update .gitignore

更新 .gitignore
2026-09-23 16:42:46 +08:00 · 2026-09-23 15:43:38 +08:00
54 changed files with 82 additions and 4312 deletions
@@ -12,12 +12,7 @@ name: build-sglang-image
 on:
  push:
-    branches: [dsv41-pd, dsv41-pd-visioncp]
+    branches: [dsv41-pd]
    # compose/部署配置 与 workflow 自身的改动不触发镜像构建（省 runner 与推送带宽）。
    # 改了 workflow 想重建镜像时，需伴随任意代码改动或手动触发。
    paths-ignore:
      - 'deploy/**'
      - '.gitea/**'
 env:
  # 直接写死 Gitea 自带 registry（vars context 在该实例上求值异常会导致回退 docker.io）
@@ -49,9 +44,7 @@ jobs:
          context: .
          file: Dockerfile.gitea
          push: true
          # cache-from: type=registry
          # cache-to: type=registry,mode=max
          tags: |
            ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.meta.outputs.tag }}
            ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ github.ref_name }}-latest
-          
+          # 注意：type=gha 缓存在本实例的 runner 上会 404（cache server 未配），勿加回
@@ -1,21 +0,0 @@
 # 优化版（2026-09-24）：解决清华源限流下每次构建重下 torch 的问题。
 # 要点：
 #  1. pyproject build-system.requires 含 torch==2.13.0，pip 隔离构建环境每次都重下 ~6GB。
 #     基底镜像已装 torch 2.13 → 用 --no-build-isolation 复用，构建环境零下载。
 #  2. 基底缺 setuptools-scm（版本打戳要用），单层预装 + pip cache mount，只下载一次。
 #  3. RUN 的 pip cache mount 持久化在宿主机，依赖解析命中的包不再重复下载。
 FROM uhub.service.ucloud.cn/umirror/sglang:dev-dsv41
 ARG PIP_INDEX=https://pypi.tuna.tsinghua.edu.cn/simple
 ENV PIP_INDEX_URL=${PIP_INDEX}
 # 构建后端（pyproject build-system.requires，torch 除外——基底已有）
 RUN --mount=type=cache,target=/root/.cache/pip \
    pip install "setuptools>=61" "setuptools-scm>=8" "setuptools-rust>=1.11" wheel
 # 整个源码树（含 .git，用于 setuptools-scm 版本打戳）
 COPY sglang/ /sgl-workspace/sglang/
 # editable 安装，全量依赖解析（pyproject.toml 变化时走这个）
 RUN --mount=type=cache,target=/root/.cache/pip \
    pip install --no-build-isolation -e /sgl-workspace/sglang/python
@@ -1,15 +0,0 @@
 # fast 路径：python/pyproject.toml 未变化时使用（build.sh 自动判断）。
 # --no-deps 跳过全部依赖解析（连 index 元数据请求都省掉），纯源码迭代秒级完成。
 # 依赖有变化时必须走 Dockerfile 全量路径（build.sh 按 pyproject sha256 自动切换）。
 FROM uhub.service.ucloud.cn/umirror/sglang:dev-dsv41
 ARG PIP_INDEX=https://pypi.tuna.tsinghua.edu.cn/simple
 ENV PIP_INDEX_URL=${PIP_INDEX}
 RUN --mount=type=cache,target=/root/.cache/pip \
    pip install "setuptools>=61" "setuptools-scm>=8" "setuptools-rust>=1.11" wheel
 COPY sglang/ /sgl-workspace/sglang/
 RUN --mount=type=cache,target=/root/.cache/pip \
    pip install --no-deps --no-build-isolation -e /sgl-workspace/sglang/python
@@ -1,33 +0,0 @@
 #!/bin/bash
 # 用法: /data/ymk/build/build.sh [tag]
 # 默认 tag: ymkymx/sglang:<分支>-<sha9>-local-<UTC构建日期时间>（命名规则见 AGENTS.md）
 # 另打 <分支>-latest-local 别名。
 #
 # 依赖路径自动选择：
 #   python/pyproject.toml 的 sha256 与上次成功构建一致 → Dockerfile.fast（--no-deps，秒级）
 #   不一致（或 FULL=1）→ Dockerfile 全量依赖解析，成功后记录新 hash
 set -euo pipefail
 cd /data/ymk
 SHA=$(git -C sglang rev-parse --short=9 HEAD)
 BR=$(git -C sglang rev-parse --abbrev-ref HEAD)
 DT=$(date -u +%Y%m%d-%H%M)
 TAG=${1:-ymkymx/sglang:$BR-$SHA-local-$DT}
 HASH_FILE=build/.last_pyproject_sha256
 CUR=$(sha256sum sglang/python/pyproject.toml | cut -d' ' -f1)
 PREV=$(cat "$HASH_FILE" 2>/dev/null || echo none)
 DOCKERFILE=build/Dockerfile
 if [ "$CUR" = "$PREV" ] && [ "${FULL:-0}" != "1" ]; then
  DOCKERFILE=build/Dockerfile.fast
  echo "== pyproject 未变，走 fast 路径（--no-deps）"
 else
  echo "== pyproject 有变化或 FULL=1，走全量依赖解析"
 fi
 echo "== building $TAG from sglang@$(git -C sglang log --oneline -1) [$DOCKERFILE]"
 docker build -f "$DOCKERFILE" -t "$TAG" .
 # 构建成功才记录 hash / 打别名
 echo "$CUR" > "$HASH_FILE"
 docker tag "$TAG" "ymkymx/sglang:$BR-latest-local"
 echo "== done: $TAG （别名 $BR-latest-local）"
@@ -1,33 +0,0 @@
 # B300 ds41 部署 compose 档案
 b300-01 上 DeepSeek-V4.1-Flash 各部署方案的 docker compose 存档。
 **本目录是 source of truth**；b300 上的运行目录 `/data/ymk/ds41/` 是工作副本。
 方案说明、参数矩阵、特殊 env、已知坑见飞书部署手册（组内共享）：
 《B300 sglang 部署手册》 https://u04wb5irxz.feishu.cn/docx/FOi8dbnybodHr0xIfkPcQ6gtnRx
 ## 同步流程
 ```bash
 # 本机（D:\B300\sglang）
 git add deploy/ && git commit -m "deploy: ..."
 git push origin dsv41-pd-visioncp   # Gitea（paths-ignore，不触发镜像构建）
 git push b300 dsv41-pd-visioncp     # b300 裸仓库
 # b300-01
 git -C /data/ymk/sglang pull        # deploy/ 出现在 /data/ymk/sglang/deploy/b300-ds41/
 ```
 ## CI 说明
 `.gitea/workflows/build-image.yaml` 的 push 触发器带 `paths-ignore: ['deploy/**', '.gitea/**']`，
 改本目录不会触发镜像构建。注意：workflow 自身的改动也不再自动触发，需要重建镜像时
 伴随代码改动 push 或手动触发。
 ## 目录规则
 - 命名：`dockerserve-<拓扑>-<特性>-<卡位>.yml`（如 `-b4` = 后 4 卡）
 - 退役文件不要留在主目录：移入 `archive-YYYYMMDD/`（b300 侧同样执行）
 - 禁止提交 `.bak` 备份文件
 - `mooncake-store.json` 是 hicache L3 mooncake store 配置，被
  `dockerserve-pd2-p-r1/r2.yml` 通过 `SGLANG_HICACHE_MOONCAKE_CONFIG_PATH` 引用
@@ -1,171 +0,0 @@
 # 3x cp2-P + 1x dp2-D PD 分离 + L3 mooncake 互联缓存 + engram host table
 # 2026-09-23 实验；基线见 archive-20260923/ 与 D:\B300\experiments\3cp2-pd\baseline-20260923.md
 # GPU: P1=0,1 P2=2,3 P3=4,5 D=6,7
 # 端口: P1=30000 P2=30010 P3=30020 D=30001 router=30002
 # bootstrap: P1=8998 P2=8999 P3=9000 D=9001
 x-sglang-common: &sglang-common
  image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
  shm_size: "32gb"
  ipc: host
  pid: host
  privileged: true
  network_mode: host
  volumes:
    - /data:/data
    - /data/ymk/cache/sglang:/root/.cache/sglang
  deploy:
    resources:
      reservations:
        devices:
          - driver: nvidia
            count: all
            capabilities: [gpu]
 x-p-environment: &p-environment
  SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE: "1"
  SGLANG_RAGGED_VERIFY_MODE: static
  MC_INTRANODE_NVLINK: "true"
  MC_INTRA_NVLINK: "true"
  SGLANG_MOONCAKE_SEND_AUX_TCP: "1"
  SGLANG_HICACHE_MOONCAKE_CONFIG_PATH: /data/ymk/ds41/mooncake-store.json
  SGLANG_DISAGGREGATION_QUEUE_SIZE: "16"
  SGLANG_DISAGGREGATION_THREAD_POOL_SIZE: "32"
 services:
  p1:
    <<: *sglang-common
    container_name: ds41-cp2-p1
    environment:
      <<: *p-environment
      CUDA_VISIBLE_DEVICES: "0,1"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --enable-prefill-cp --cp-strategy interleave
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30000
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
      --disaggregation-bootstrap-port 8998
  p2:
    <<: *sglang-common
    container_name: ds41-cp2-p2
    environment:
      <<: *p-environment
      CUDA_VISIBLE_DEVICES: "2,3"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --enable-prefill-cp --cp-strategy interleave
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30010
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
      --disaggregation-bootstrap-port 8999
  p3:
    <<: *sglang-common
    container_name: ds41-cp2-p3
    environment:
      <<: *p-environment
      CUDA_VISIBLE_DEVICES: "4,5"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --enable-prefill-cp --cp-strategy interleave
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30020
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
      --disaggregation-bootstrap-port 9000
  d:
    <<: *sglang-common
    container_name: ds41-cp2-d
    environment:
      SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE: "1"
      SGLANG_RAGGED_VERIFY_MODE: static
      MC_INTRANODE_NVLINK: "true"
      MC_INTRA_NVLINK: "true"
      SGLANG_MOONCAKE_SEND_AUX_TCP: "1"
      SGLANG_DISAGGREGATION_QUEUE_SIZE: "16"
      SGLANG_DISAGGREGATION_THREAD_POOL_SIZE: "32"
      CUDA_VISIBLE_DEVICES: "6,7"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2 --dp-size 2
      --enable-dp-attention --enable-dp-lm-head
      --mem-fraction-static 0.80
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30001
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --disaggregation-mode decode
      --disaggregation-transfer-backend mooncake
      --disaggregation-bootstrap-port 9001
@@ -1,43 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:main-ee5fcdf0d-20260920-0142
    container_name: ds41-sglang-b4
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30001:30000"
    environment:
      - CUDA_VISIBLE_DEVICES=4,5,6,7
      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.60
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --dp-size 4
      --enable-dp-attention
      --enable-cache-report
      --enable-metrics
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,43 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:main-ee5fcdf0d-20260920-0142
    container_name: ds41-sglang-b4
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30001:30000"
    environment:
      - CUDA_VISIBLE_DEVICES=4,5,6,7
      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.60
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --enable-decoder-swa-bounded-replay
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --enable-metrics
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,42 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:main-ee5fcdf0d-20260920-0142
    container_name: ds41-sglang-b4
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30001:30000"
    environment:
      - CUDA_VISIBLE_DEVICES=4,5,6,7
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --enable-decoder-swa-bounded-replay
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-prefill-cp
      --cp-strategy interleave
      --enable-cache-report
      --enable-metrics
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,160 +0,0 @@
 # 4×cp2 独立实例（非 PD）+ hicache L3(mooncake) + dspark + engram host table 卸载（2026-09-23 晚）
 # 用户指定组合：4 cp2 hicache l3 dspark roundrobin loadbalance engram offload
 # 每实例：tp2 ep2 + interleave CP2 + dspark b5 + hicache L3 write_through(size 0) + engram host table
 # （tp2 权重必须靠 engram 卸载才放得下，见 goals-track G1.9 反转）
 # GPU: a=0,1 b=2,3 c=4,5 d=6,7；端口: 30000/30010/30020/30030；rr router=30002
 # 参考：dockerserve-cpdspark-l3.yml（hicache 参数）、dockerserve-3cp2-pd.yml（cp2/engram 参数）
 x-common: &common
  image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
  shm_size: "32gb"
  ipc: host
  privileged: true
  network_mode: host
  volumes:
    - /data:/data
    - /data/ymk/cache/sglang:/root/.cache/sglang
    # 热补丁（2026-09-23）：CP 对称 idle 检查，修 health-check × hicache drain 死锁
    # 源文件：/data/ymk/sglang（dsv41-pd-visioncp 分支工作区已改）；补丁脚本见
    # D:\B300\experiments\cp2x4\patch_healthcheck_cp_idle.py
    - /data/ymk/sglang/python/sglang/srt/managers/scheduler.py:/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py
  environment: &env
    SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE: "1"
    SGLANG_RAGGED_VERIFY_MODE: static
    MC_MS_AUTO_DISC: "0"
    MOONCAKE_MASTER: 127.0.0.1:50051
    MOONCAKE_TE_META_DATA_SERVER: P2PHANDSHAKE
    MOONCAKE_PROTOCOL: tcp
    MOONCAKE_GLOBAL_SEGMENT_SIZE: 300gb
  deploy:
    resources:
      reservations:
        devices:
          - driver: nvidia
            count: all
            capabilities: [gpu]
 services:
  a:
    <<: *common
    container_name: ds41-cp2-a
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "0,1"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --enable-prefill-cp --cp-strategy interleave
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30000
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
  b:
    <<: *common
    container_name: ds41-cp2-b
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "2,3"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --enable-prefill-cp --cp-strategy interleave
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30010
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
  c:
    <<: *common
    container_name: ds41-cp2-c
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "4,5"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --enable-prefill-cp --cp-strategy interleave
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30020
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
  d:
    <<: *common
    container_name: ds41-cp2-d2
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "6,7"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --enable-prefill-cp --cp-strategy interleave
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30030
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
@@ -1,44 +0,0 @@
 # cp8 单机非 PD 测试（2026-09-23 晚）
 # 背景：dp8 单机 dspark 健康但长上下文 prefill 结构性慢（单请求只落 1 rank），
 #       换 cp8（tp8 + interleave prefill CP8，单请求 prefill 切到 8 卡）对照。
 #       关 engram、无 hicache L3、无 PD。cp+dspark 无 replay 是已知健康组合
 #       （cp4+dspark+replay 三元组必崩，本配置不开 replay）。
 # GPU 0-7，端口 30000，容器 ds41-cp8，project cp8
 services:
  cp8:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-cp8
    shm_size: "32gb"
    ipc: host
    privileged: true
    network_mode: host
    environment:
      SGLANG_RAGGED_VERIFY_MODE: "static"
      CUDA_VISIBLE_DEVICES: "0,1,2,3,4,5,6,7"
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 8 --ep-size 8
      --enable-prefill-cp --cp-strategy interleave
      --mem-fraction-static 0.80
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30000
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
@@ -1,50 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-ddf520763-local-20260923-0536
    container_name: ds41-cpdspark-l3-b
    shm_size: "32gb"
    ipc: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=4,5,6,7
      - MC_MS_AUTO_DISC=0
      - MOONCAKE_MASTER=127.0.0.1:50051
      - MOONCAKE_TE_META_DATA_SERVER=P2PHANDSHAKE
      - MOONCAKE_PROTOCOL=tcp
      - MOONCAKE_GLOBAL_SEGMENT_SIZE=400gb
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4 --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto --tool-call-parser auto
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30001
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-prefill-cp --cp-strategy interleave
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,51 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-ddf520763-local-20260923-0536
    container_name: ds41-cpdspark-l3-b
    shm_size: "32gb"
    ipc: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=4,5,6,7
      - MC_MS_AUTO_DISC=0
      - MOONCAKE_MASTER=127.0.0.1:50051
      - MOONCAKE_TE_META_DATA_SERVER=P2PHANDSHAKE
      - MOONCAKE_PROTOCOL=tcp
      - MOONCAKE_GLOBAL_SEGMENT_SIZE=400gb
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4 --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto --tool-call-parser auto
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30001
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-prefill-cp --cp-strategy interleave
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,50 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-ddf520763-local-20260923-0536
    container_name: ds41-cpdspark-l3-a
    shm_size: "32gb"
    ipc: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
      - MC_MS_AUTO_DISC=0
      - MOONCAKE_MASTER=127.0.0.1:50051
      - MOONCAKE_TE_META_DATA_SERVER=P2PHANDSHAKE
      - MOONCAKE_PROTOCOL=tcp
      - MOONCAKE_GLOBAL_SEGMENT_SIZE=400gb
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4 --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto --tool-call-parser auto
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30000
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-prefill-cp --cp-strategy interleave
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,51 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-ddf520763-local-20260923-0536
    container_name: ds41-cpdspark-l3-a
    shm_size: "32gb"
    ipc: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
      - MC_MS_AUTO_DISC=0
      - MOONCAKE_MASTER=127.0.0.1:50051
      - MOONCAKE_TE_META_DATA_SERVER=P2PHANDSHAKE
      - MOONCAKE_PROTOCOL=tcp
      - MOONCAKE_GLOBAL_SEGMENT_SIZE=400gb
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4 --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto --tool-call-parser auto
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30000
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-prefill-cp --cp-strategy interleave
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,44 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-92632a60b-20260922-2100
    container_name: ds41-cpdspark-nr-b4
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30001:30001"
    environment:
      - CUDA_VISIBLE_DEVICES=4,5,6,7
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-prefill-cp
      --cp-strategy interleave
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,44 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-92632a60b-20260922-2100
    container_name: ds41-cpdspark-nr
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30000:30000"
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-prefill-cp
      --cp-strategy interleave
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,44 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:main-ee5fcdf0d-20260920-0142
    container_name: ds41-cpdspark
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30000:30000"
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-prefill-cp
      --cp-strategy interleave
      --enable-decoder-swa-bounded-replay
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,62 +0,0 @@
 # dp2 对照（2026-09-24 上午）：验证 dp2（dp-attention）下 dspark 是否正常。
 # 与 dockerserve-tp2.yml 逐参数对齐，唯一差异 = 加 --dp-size 2 --enable-dp-attention --enable-dp-lm-head。
 # GPU 6-7，端口 30030 直连。镜像/补丁挂载/L3/engram/tok8 全部相同。
 # 注：dp+dspark 不能开 --enable-decoder-swa-bounded-replay（本配置本来就没开）。
 x-common: &common
  image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
  shm_size: "32gb"
  ipc: host
  privileged: true
  network_mode: host
  volumes:
    - /data:/data
    - /data/ymk/cache/sglang:/root/.cache/sglang
    - /data/ymk/sglang/python/sglang/srt/managers/scheduler.py:/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py
  environment: &env
    SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE: "1"
    SGLANG_RAGGED_VERIFY_MODE: static
    MC_MS_AUTO_DISC: "0"
    MOONCAKE_MASTER: 127.0.0.1:50051
    MOONCAKE_TE_META_DATA_SERVER: P2PHANDSHAKE
    MOONCAKE_PROTOCOL: tcp
    MOONCAKE_GLOBAL_SEGMENT_SIZE: 300gb
  deploy:
    resources:
      reservations:
        devices:
          - driver: nvidia
            count: all
            capabilities: [gpu]
 services:
  dp2:
    <<: *common
    container_name: ds41-dp2
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "6,7"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --dp-size 2 --enable-dp-attention --enable-dp-lm-head
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30030
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
@@ -1,42 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:main-ee5fcdf0d-20260920-0142
    container_name: ds41-dp4test
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30000:30000"
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --enable-decoder-swa-bounded-replay
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-prefill-cp
      --cp-strategy interleave
      --enable-cache-report
      --enable-metrics
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,44 +0,0 @@
 # dp8+tp8 单机非 PD 对照测试（2026-09-23 晚）
 # 背景：3cp2+dp2 PD 部署 dspark accept 回归（32k ctx accept len 3.14→1.31，
 #       见 experiments/3cp2-pd/bench-20260923.md「未决问题」）。本配置退回单机验证
 #       dspark 健康度：engram host table 关闭、无 hicache L3、无 PD、无 mooncake。
 # 参数基准：dockerserve-3cp2-pd.yml 的 d 服务（dp 路径），去掉 PD/L3/engram 相关。
 # GPU 0-7，端口 30000，容器 ds41-dp8，project dp8
 services:
  dp8:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-dp8
    shm_size: "32gb"
    ipc: host
    privileged: true
    network_mode: host
    environment:
      SGLANG_RAGGED_VERIFY_MODE: "static"
      CUDA_VISIBLE_DEVICES: "0,1,2,3,4,5,6,7"
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 8 --ep-size 8 --dp-size 8
      --enable-dp-attention --enable-dp-lm-head
      --mem-fraction-static 0.80
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30000
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
@@ -1,47 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:main-ee5fcdf0d-20260920-0142
    container_name: ds41-prefill
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30000:30000"
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-decoder-swa-bounded-replay
      --enable-hierarchical-cache
      --hicache-ratio 2.5
      --hicache-write-policy write_back
      --disaggregation-mode prefill
      --optimistic-prefill-attempts 4
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,51 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-pd-decode
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=4,5,6,7
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --dp-size 4
      --enable-dp-attention
      --enable-dp-lm-head
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --tokenizer-worker-num 8
      --host 0.0.0.0
      --port 30001
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --disaggregation-mode decode
      --disaggregation-transfer-backend mooncake
@@ -1,50 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-ddf520763-local-20260923-0536
    container_name: ds41-pd-decode
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=4,5,6,7
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --dp-size 4
      --enable-dp-attention
      --enable-dp-lm-head
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --tokenizer-worker-num 8
      --host 0.0.0.0
      --port 30001
      --enable-cache-report
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --disaggregation-mode decode
      --disaggregation-transfer-backend mooncake
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,55 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-c74a4037f-20260921-1300
    container_name: ds41-pd-prefill-dp
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --dp-size 4
      --enable-dp-attention
      --enable-dp-lm-head
      --load-balance-method total_tokens
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30010
      --enable-cache-report
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2.5
      --hicache-write-policy write_back
      --disaggregation-mode prefill
      --disaggregation-bootstrap-port 8918
      --disaggregation-transfer-backend mooncake
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,53 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-pd-prefill
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --tokenizer-worker-num 8
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2.5
      --hicache-write-policy write_back
      --enable-prefill-cp
      --cp-strategy interleave
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
@@ -1,52 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-ddf520763-local-20260923-0536
    container_name: ds41-pd-prefill
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --tokenizer-worker-num 8
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2.5
      --hicache-write-policy write_back
      --enable-prefill-cp
      --cp-strategy interleave
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,57 +0,0 @@
 # PD2 二分 Round 2 D 侧（2026-09-24）：干净 D + 嫌疑项②
 # SGLANG_DISAGGREGATION_QUEUE_SIZE=16 + SGLANG_DISAGGREGATION_THREAD_POOL_SIZE=32
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-pd2-decode
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=6,7
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
      - SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE=1
      - SGLANG_DISAGGREGATION_QUEUE_SIZE=16
      - SGLANG_DISAGGREGATION_THREAD_POOL_SIZE=32
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
      - /data/ymk/sglang/python/sglang/srt/managers/scheduler.py:/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2
      --ep-size 2
      --dp-size 2
      --enable-dp-attention
      --enable-dp-lm-head
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto
      --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --tokenizer-worker-num 8
      --host 0.0.0.0
      --port 30030
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --disaggregation-mode decode
      --disaggregation-transfer-backend mooncake
@@ -1,54 +0,0 @@
 # PD 干净对照实验 D 节点（2026-09-24 上午）：dp2 decode，配 dockerserve-pd2-p.yml 使用。
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-pd2-decode
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=6,7
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
      - SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE=1
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
      - /data/ymk/sglang/python/sglang/srt/managers/scheduler.py:/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2
      --ep-size 2
      --dp-size 2
      --enable-dp-attention
      --enable-dp-lm-head
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto
      --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --tokenizer-worker-num 8
      --host 0.0.0.0
      --port 30030
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --disaggregation-mode decode
      --disaggregation-transfer-backend mooncake
@@ -1,67 +0,0 @@
 # PD2 二分 Round 1（2026-09-24）：干净基线 + 嫌疑项①「P 侧 L3 hicache 块 + mooncake-store.json」
 # 相对 dockerserve-pd2-p.yml 的差异：
 #   env 加 SGLANG_HICACHE_MOONCAKE_CONFIG_PATH=/data/ymk/ds41/mooncake-store.json
 #   hicache 参数块换成坏部署同款：page_first_direct + direct + write_through + mooncake +
 #     wait_complete + size 0（替代 write_back L2）
 # D 侧不变（坏部署 D 本无 L3）。探针：bs16 low_entropy decode 看 accept len。
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-pd2-prefill
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=4,5
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
      - SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE=1
      - SGLANG_HICACHE_MOONCAKE_CONFIG_PATH=/data/ymk/ds41/mooncake-store.json
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
      - /data/ymk/sglang/python/sglang/srt/managers/scheduler.py:/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2
      --ep-size 2
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto
      --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --tokenizer-worker-num 8
      --host 0.0.0.0
      --port 30020
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
      --enable-prefill-cp
      --cp-strategy interleave
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
@@ -1,65 +0,0 @@
 # PD2 二分 Round 2 P 侧（2026-09-24）：R1（L3 块）之上再加嫌疑项②
 # SGLANG_DISAGGREGATION_QUEUE_SIZE=16 + SGLANG_DISAGGREGATION_THREAD_POOL_SIZE=32
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-pd2-prefill
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=4,5
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
      - SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE=1
      - SGLANG_HICACHE_MOONCAKE_CONFIG_PATH=/data/ymk/ds41/mooncake-store.json
      - SGLANG_DISAGGREGATION_QUEUE_SIZE=16
      - SGLANG_DISAGGREGATION_THREAD_POOL_SIZE=32
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
      - /data/ymk/sglang/python/sglang/srt/managers/scheduler.py:/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2
      --ep-size 2
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto
      --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --tokenizer-worker-num 8
      --host 0.0.0.0
      --port 30020
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
      --enable-prefill-cp
      --cp-strategy interleave
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
@@ -1,59 +0,0 @@
 # PD 干净对照实验（2026-09-24 上午）：验证「cp2-P → dp2-D」传输路径下 dspark 是否正常。
 # 用户疑问：单机六形态健康不等于 PD 链路健康，可能两边传输没对齐。
 # 以已验证可用的 dockerserve-pd-{p,d}-vision.yml 为底，缩到 2+2 卡；P 加 engram host table
 # （2 卡权重放不下，见 G1.9）。P=GPU4-5 端口 30020，D=GPU6-7 端口 30030，mini_lb=30004。
 services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-pd2-prefill
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=4,5
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
      - SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE=1
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
      - /data/ymk/sglang/python/sglang/srt/managers/scheduler.py:/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2
      --ep-size 2
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto
      --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --tokenizer-worker-num 8
      --host 0.0.0.0
      --port 30020
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2.5
      --hicache-write-policy write_back
      --enable-prefill-cp
      --cp-strategy interleave
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
@@ -1,42 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:main-ee5fcdf0d-20260920-0142
    container_name: ds41-replay-off
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30000:30000"
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,42 +0,0 @@
 services:
  sglang:
    image: ymkymx/sglang:main-ee5fcdf0d-20260920-0142
    container_name: ds41-replay-on
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30000:30000"
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-decoder-swa-bounded-replay
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,92 +0,0 @@
 # 纯 tp2 单实例对照（2026-09-24 早）：与 dockerserve-cp2x4.yml 逐参数对齐，唯一差异 = 去掉
 # --enable-prefill-cp --cp-strategy interleave（即无 CP），用于测「tp2 vs cp2」的 prefill 效率差。
 # GPU 4-5(a)/6-7(b)，端口 30020/30030；2×tp2 聚合经 rr router 30003。
 # 镜像/补丁挂载/L3/engram/tok8 全部与 cp2x4 相同。
 x-common: &common
  image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
  shm_size: "32gb"
  ipc: host
  privileged: true
  network_mode: host
  volumes:
    - /data:/data
    - /data/ymk/cache/sglang:/root/.cache/sglang
    # 与 cp2x4 保持同一份 scheduler.py（含未 commit 的 CP idle 补丁），保证唯一变量是 CP 开关
    - /data/ymk/sglang/python/sglang/srt/managers/scheduler.py:/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py
  environment: &env
    SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE: "1"
    SGLANG_RAGGED_VERIFY_MODE: static
    MC_MS_AUTO_DISC: "0"
    MOONCAKE_MASTER: 127.0.0.1:50051
    MOONCAKE_TE_META_DATA_SERVER: P2PHANDSHAKE
    MOONCAKE_PROTOCOL: tcp
    MOONCAKE_GLOBAL_SEGMENT_SIZE: 300gb
  deploy:
    resources:
      reservations:
        devices:
          - driver: nvidia
            count: all
            capabilities: [gpu]
 services:
  tp2:
    <<: *common
    container_name: ds41-tp2
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "4,5"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30020
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
  b:
    <<: *common
    container_name: ds41-tp2-b
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "6,7"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30030
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
@@ -1,43 +0,0 @@
 services:
  sglang:
    image: uhub.service.ucloud.cn/umirror/sglang:dev-dsv41
    shm_size: "32gb"
    ipc: host
    privileged: true
    ports:
      - "30000:30000"
    volumes:
      - /data:/data
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --enable-decoder-swa-bounded-replay
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --enable-metrics
      --enable-prefill-cp 
      --cp-strategy interleave
      --json-model-override-args '{"vision_n_layers": 0}'
@@ -1,6 +0,0 @@
 {
  "master_server_address": "127.0.0.1:50051",
  "metadata_server": "P2PHANDSHAKE",
  "global_segment_size": "300gb",
  "protocol": "tcp"
 }
@@ -181,15 +181,12 @@ def validate_deepseek_v41_features(server_args: ServerArgs) -> None:
    )
    cfg = resolving_view(server_args)
-    hf_config = model_config_of(server_args).hf_config
+    if model_config_of(server_args).hf_config.model_type != "deepseek_v41":
    if hf_config.model_type != "deepseek_v41":
        if cfg.enable_encoder_swa_bounded_replay:
            raise ValueError(
                "--enable-encoder-swa-bounded-replay requires DeepSeek-V4.1"
            )
        return
    if hf_config.vision_n_layers > 0 and cfg.enable_prefill_cp:
        _validate_deepseek_v41_vision_prefill_cp(server_args)
    if cfg.enable_encoder_swa_bounded_replay:
        from sglang.srt.model_executor.cuda_graph_config import Backend
@@ -200,8 +197,7 @@ def validate_deepseek_v41_features(server_args: ServerArgs) -> None:
                cfg.cuda_graph_config.prefill.backend != Backend.DISABLED,
            ),
            ("DP attention", cfg.enable_dp_attention),
-            # Prefill CP declares attn_cp_size and DP attention only later.
+            ("context parallelism", cfg.attn_cp_size > 1),
            ("context parallelism", cfg.attn_cp_size > 1 or cfg.enable_prefill_cp),
            ("external cache linker", cfg.enable_unified_cache_external_linker),
            ("unified memory", cfg.enable_unified_memory),
            ("PD disaggregation", cfg.disaggregation_mode != "null"),
@@ -310,40 +306,3 @@ def validate_deepseek_v41_features(server_args: ServerArgs) -> None:
                    "--enable-decoder-swa-bounded-replay cannot be combined with "
                    f"{feature} yet; disable one of them."
                )
 def _validate_deepseek_v41_vision_prefill_cp(server_args: ServerArgs) -> None:
    from sglang.srt.model_executor.cuda_graph_config import Backend, Phase, with_phase
    cfg = resolving_view(server_args)
    if cfg.cp_strategy != "interleave":
        raise ValueError(
            "DeepSeek-V4.1 vision with prefill CP requires --cp-strategy "
            f"interleave; got {cfg.cp_strategy!r}."
        )
    if cfg.cuda_graph_config.prefill.backend != Backend.DISABLED:
        # The CP runner merges image features eagerly; no capture path replays it.
        locked = getattr(server_args, "_cuda_graph_config_locked", set())
        if (Phase.PREFILL, "backend") in locked:
            raise ValueError(
                "DeepSeek-V4.1 vision with prefill CP runs eager prefill; remove "
                "the explicit prefill CUDA graph backend."
            )
        declare_resolution(
            server_args,
            "validate_deepseek_v41_features",
            cuda_graph_config=with_phase(
                cfg.cuda_graph_config, Phase.PREFILL, backend=Backend.DISABLED
            ),
        )
        logger.warning(
            "Disabling the prefill CUDA graph for DeepSeek-V4.1 vision with prefill CP."
        )
    if (
        str(cfg.speculative_algorithm).upper() == "DSPARK"
        and cfg.enable_decoder_swa_bounded_replay
    ):
        raise ValueError(
            "DeepSeek-V4.1 vision with prefill CP does not support DSpark together "
            "with --enable-decoder-swa-bounded-replay yet."
        )
@@ -1,486 +0,0 @@
 """One owner rank encodes each image span and broadcasts it to the ranks that
 run the same prefill chunk; every agreement precedes the payload it guards."""
 from __future__ import annotations
 import logging
 from contextlib import contextmanager
 from typing import Any, Callable, Dict, Iterator, List, Optional, Sequence, Tuple
 import msgspec
 import torch
 from sglang.srt.distributed.device_communicators.pynccl_allocator import (
    disable_symmetric_memory_context,
    restore_symmetric_memory_context,
 )
 from sglang.srt.mem_cache.multimodal_cache import EmbeddingResult, MultiModalStaticCache
 logger = logging.getLogger(__name__)
 SpanKey = Tuple[Optional[int], int]
 SpanEncoder = Callable[[List[Any]], torch.Tensor | List[torch.Tensor]]
 SpanSignature = Callable[[Any, int], Tuple[Any, ...]]
 LOCAL_HIT = 0
 OWNER_CACHE_BROADCAST = 1
 OWNER_ENCODE_BROADCAST = 2
 PHASE_PREPARE = "prepare"
 PHASE_FEATURES = "features"
 PHASE_FINALIZE = "finalize"
 class MmOwnerProtocolError(RuntimeError):
    """Raised with identical text on every group member after a group-agreed failure."""
 class ImageSpanRequest(msgspec.Struct, frozen=True):
    hash: Optional[int]
    span_len: int
    item: Any
    inside_chunk: bool
    duplicates: List[Any] = []
 class ImageSpanKey(msgspec.Struct, frozen=True):
    hash: Optional[int]
    span_len: int
    geometry: Optional[Tuple[Any, ...]]
 class RankManifest(msgspec.Struct, frozen=True):
    rank: int
    keys: List[ImageSpanKey]
    cached: List[bool]
    dtype: str
    width: int
    rids: List[str]
    error: Optional[str] = None
 class OwnerPlan(msgspec.Struct, frozen=True):
    actions: List[int]
    owners: List[int]
    error: Optional[str] = None
 class RankStatus(msgspec.Struct, frozen=True):
    rank: int
    error: Optional[str] = None
 def select_owner_group(parallel) -> Optional[Any]:
    """The group whose members all execute the same requests, or None when a
    single rank already encodes every image it sees."""
    replication = parallel.tp_size // parallel.attn_dp_size
    if replication <= 1:
        return None
    if parallel.attn_cp_size == 1:
        group = parallel.attn_tp_group
    elif parallel.attn_dp_size == 1 and parallel.attn_cp_size == parallel.tp_size:
        group = parallel.attn_cp_group
    else:
        return None
    return group if group.world_size == replication else None
 def has_owner_span_work(
    mm_inputs: Sequence[Any],
    extend_prefix_lens: Sequence[int],
    extend_seq_lens: Sequence[int],
 ) -> bool:
    """Host-side mirror of the per-image scheduling path: does any raw
    single-span image overlap the chunk on every rank of the group."""
    for mm_input, prefix_len, extend_len in zip(
        mm_inputs, extend_prefix_lens, extend_seq_lens
    ):
        if mm_input is None or extend_len <= 0:
            continue
        items = [item for item in mm_input.mm_items if item is not None]
        if not items or any(
            item.precomputed_embeddings is not None or len(item.offsets) != 1
            for item in items
        ):
            continue
        for item in items:
            start, end = item.offsets[0]
            if end >= prefix_len and start < prefix_len + extend_len:
                return True
    return False
 class MmOwnerSession(msgspec.Struct):
    group: Any
    device: Any
    dtype: Any
    width: int
    rids: List[str]
    signature: Any
    engaged: bool
    phase: str = PHASE_PREPARE
    in_collective: bool = False
    def resolve(
        self,
        requests: Sequence[ImageSpanRequest],
        cache: MultiModalStaticCache,
        encode: SpanEncoder,
    ) -> Dict[SpanKey, torch.Tensor]:
        if not self.engaged:
            raise RuntimeError(
                "owner protocol reached for a chunk whose host metadata has no image span"
            )
        # Owners allocate different amounts than receivers, so none of these
        # buffers may come out of a symmetric pool.
        saved_context = disable_symmetric_memory_context()
        try:
            return _resolve_owner_features(self, requests, cache, encode)
        finally:
            restore_symmetric_memory_context(saved_context)
    def features_ready(self) -> None:
        self._complete()
        self.phase = PHASE_FINALIZE
    @contextmanager
    def uncaptured(self) -> Iterator[None]:
        # A failure inside a collective leaves the group in an unknown state;
        # no later exchange may try to agree on it.
        self.in_collective = True
        yield
        self.in_collective = False
    @contextmanager
    def fence(self) -> Iterator[None]:
        try:
            yield
        except Exception as exc:
            self._fail(exc)
            raise
        self._complete()
    def _fail(self, exc: BaseException) -> None:
        if (
            not self.engaged
            or self.in_collective
            or isinstance(exc, MmOwnerProtocolError)
        ):
            raise exc
        text = _describe(self, self.phase, exc)
        if self.phase == PHASE_PREPARE:
            try:
                _exchange_manifest(self, _manifest(self, [], [], error=text))
            except MmOwnerProtocolError as agreed:
                raise agreed from exc
        _exchange_status(self, text, exc)
    def _complete(self) -> None:
        if not self.engaged:
            return
        if self.phase == PHASE_PREPARE:
            raise RuntimeError(
                f"owner protocol {self.phase} completed without a manifest exchange"
            )
        error = None
        cause = None
        try:
            _synchronize(self.device)
        except Exception as exc:
            cause = exc
            error = _describe(self, self.phase, exc)
        _exchange_status(self, error, cause)
 def _manifest(
    session: MmOwnerSession,
    keys: List[ImageSpanKey],
    cached: List[bool],
    error: Optional[str] = None,
 ) -> RankManifest:
    return RankManifest(
        rank=session.group.rank_in_group,
        keys=keys,
        cached=cached,
        dtype=str(session.dtype),
        width=session.width,
        rids=list(session.rids),
        error=error,
    )
 def _exchange_manifest(session: MmOwnerSession, manifest: RankManifest) -> OwnerPlan:
    group = session.group
    with session.uncaptured():
        manifests = group.all_gather_object(manifest)
        plan = _plan_or_error(session, manifests) if group.rank_in_group == 0 else None
        plan = group.broadcast_object(plan, src=0)
    session.phase = PHASE_FEATURES
    if plan.error is not None:
        raise MmOwnerProtocolError(plan.error)
    return plan
 def _plan_or_error(session: MmOwnerSession, manifests: List[RankManifest]) -> OwnerPlan:
    try:
        return _make_plan(manifests)
    except Exception as exc:
        return OwnerPlan(actions=[], owners=[], error=_describe(session, "plan", exc))
 def _exchange_status(
    session: MmOwnerSession, error: Optional[str], cause: Optional[BaseException]
 ) -> None:
    with session.uncaptured():
        statuses = session.group.all_gather_object(
            RankStatus(rank=session.group.rank_in_group, error=error)
        )
    _raise_first_error(statuses, cause)
 def _resolve_owner_features(
    session: MmOwnerSession,
    requests: Sequence[ImageSpanRequest],
    cache: MultiModalStaticCache,
    encode: SpanEncoder,
 ) -> Dict[SpanKey, torch.Tensor]:
    group = session.group
    features: Dict[SpanKey, torch.Tensor] = {}
    keys: List[ImageSpanKey] = []
    cached: List[bool] = []
    error = None
    try:
        keys, cached = _pin_local_cache(session, requests, cache, features)
    except Exception as exc:
        error = _describe(session, "manifest", exc)
    plan = _exchange_manifest(session, _manifest(session, keys, cached, error))
    if all(action == LOCAL_HIT for action in plan.actions):
        return features
    buffers: Dict[int, torch.Tensor] = {}
    error = None
    try:
        buffers = _prepare_transfers(session, requests, keys, plan, features, encode)
        _synchronize(session.device)
    except Exception as exc:
        error = _describe(session, "encode", exc)
    _exchange_status(session, error, None)
    with session.uncaptured():
        for index, (action, owner) in enumerate(zip(plan.actions, plan.owners)):
            if action != LOCAL_HIT:
                group.broadcast(buffers[index], src=owner)
    for index, key in enumerate(keys):
        if plan.actions[index] == LOCAL_HIT:
            continue
        span = buffers[index]
        features[(key.hash, key.span_len)] = span
        cache.set(key.hash, EmbeddingResult(embedding=span))
    return features
 def _pin_local_cache(
    session: MmOwnerSession,
    requests: Sequence[ImageSpanRequest],
    cache: MultiModalStaticCache,
    features: Dict[SpanKey, torch.Tensor],
 ) -> Tuple[List[ImageSpanKey], List[bool]]:
    keys: List[ImageSpanKey] = []
    cached: List[bool] = []
    for request in requests:
        if request.hash is None:
            raise ValueError(
                f"image span of {request.span_len} tokens has no content hash"
            )
        geometry = session.signature(request.item, request.span_len)
        for duplicate in request.duplicates:
            other = session.signature(duplicate, request.span_len)
            if other != geometry:
                raise ValueError(
                    f"image hash {request.hash} ({request.span_len} tokens) occurs "
                    f"with different geometry: {geometry} vs {other}"
                )
        keys.append(
            ImageSpanKey(
                hash=request.hash, span_len=request.span_len, geometry=geometry
            )
        )
        span = _valid_cached_span(session, cache, request)
        if span is not None:
            features[(request.hash, request.span_len)] = span
        cached.append(span is not None)
    return keys, cached
 def _valid_cached_span(
    session: MmOwnerSession,
    cache: MultiModalStaticCache,
    request: ImageSpanRequest,
 ) -> Optional[torch.Tensor]:
    entry = cache.get_single(request.hash)
    if entry is None:
        return None
    span = entry.embedding
    if (
        span.dim() == 2
        and span.shape[0] == request.span_len
        and span.shape[1] == session.width
        and span.dtype == session.dtype
        and span.device == session.device
    ):
        return span
    logger.warning(
        "Discarding cached multimodal embedding that cannot serve the current "
        "image span: cache_key=%s expected=(%d, %d, %s) cached=(%s, %s).",
        request.hash,
        request.span_len,
        session.width,
        session.dtype,
        tuple(span.shape),
        span.dtype,
    )
    cache.free(request.hash, None)
    return None
 def _make_plan(manifests: List[RankManifest]) -> OwnerPlan:
    for manifest in manifests:
        if manifest.error is not None:
            return OwnerPlan(actions=[], owners=[], error=manifest.error)
    lead = manifests[0]
    for manifest in manifests[1:]:
        if (manifest.keys, manifest.dtype, manifest.width, manifest.rids) != (
            lead.keys,
            lead.dtype,
            lead.width,
            lead.rids,
        ):
            return OwnerPlan(
                actions=[],
                owners=[],
                error=(
                    "image manifest mismatch between group ranks 0 and "
                    f"{manifest.rank}: rids={lead.rids} vs {manifest.rids}, "
                    f"keys={lead.keys} vs {manifest.keys}, "
                    f"dtype={lead.dtype} vs {manifest.dtype}, "
                    f"width={lead.width} vs {manifest.width}"
                ),
            )
    replication = len(manifests)
    actions: List[int] = []
    owners: List[int] = []
    for index, key in enumerate(lead.keys):
        owner = key.hash % replication
        if all(manifest.cached[index] for manifest in manifests):
            action = LOCAL_HIT
        elif manifests[owner].cached[index]:
            action = OWNER_CACHE_BROADCAST
        else:
            action = OWNER_ENCODE_BROADCAST
        actions.append(action)
        owners.append(owner)
    return OwnerPlan(actions=actions, owners=owners)
 def _prepare_transfers(
    session: MmOwnerSession,
    requests: Sequence[ImageSpanRequest],
    keys: List[ImageSpanKey],
    plan: OwnerPlan,
    features: Dict[SpanKey, torch.Tensor],
    encode: SpanEncoder,
 ) -> Dict[int, torch.Tensor]:
    rank = session.group.rank_in_group
    buffers: Dict[int, torch.Tensor] = {}
    owned: List[int] = []
    for index, (action, owner) in enumerate(zip(plan.actions, plan.owners)):
        if action == LOCAL_HIT:
            continue
        if owner != rank:
            try:
                buffers[index] = _new_span_buffer(session, keys[index])
            except Exception as exc:
                raise RuntimeError(
                    f"receive buffer for image hash {keys[index].hash} shape "
                    f"{(keys[index].span_len, session.width)} {session.dtype} "
                    f"failed: {type(exc).__name__}: {exc}"
                ) from exc
        elif action == OWNER_CACHE_BROADCAST:
            key = (keys[index].hash, keys[index].span_len)
            buffers[index] = features[key].contiguous()
        else:
            owned.append(index)
    if owned:
        owned_hashes = [keys[index].hash for index in owned]
        try:
            encoded = encode([requests[index].item for index in owned])
        except Exception as exc:
            raise RuntimeError(
                f"owner encode of image hashes {owned_hashes} failed: "
                f"{type(exc).__name__}: {exc}"
            ) from exc
        spans = _split_spans(encoded, [keys[index].span_len for index in owned])
        for index, span in zip(owned, spans):
            buffers[index] = _validated_span(session, keys[index], span)
    return buffers
 def _new_span_buffer(session: MmOwnerSession, key: ImageSpanKey) -> torch.Tensor:
    return torch.empty(
        (key.span_len, session.width), device=session.device, dtype=session.dtype
    )
 def _split_spans(
    encoded: torch.Tensor | List[torch.Tensor], span_lens: List[int]
 ) -> List[torch.Tensor]:
    if isinstance(encoded, list):
        if len(encoded) != len(span_lens):
            raise ValueError(
                f"encoder returned {len(encoded)} spans for {len(span_lens)} images"
            )
        return [span.reshape(-1, span.shape[-1]) for span in encoded]
    encoded = encoded.reshape(-1, encoded.shape[-1])
    if encoded.shape[0] != sum(span_lens):
        raise ValueError(
            f"encoder returned {encoded.shape[0]} rows for spans of {span_lens}"
        )
    return list(torch.split(encoded, span_lens, dim=0))
 def _validated_span(
    session: MmOwnerSession, key: ImageSpanKey, span: torch.Tensor
 ) -> torch.Tensor:
    expected = (key.span_len, session.width)
    if tuple(span.shape) != expected or span.dtype != session.dtype:
        raise ValueError(
            f"encoded span for hash={key.hash} has shape {tuple(span.shape)} "
            f"dtype {span.dtype}; expected {expected} {session.dtype}"
        )
    if span.device != session.device:
        span = span.to(session.device)
    return span.contiguous()
 def _synchronize(device) -> None:
    if device.type == "cuda":
        torch.cuda.current_stream(device).synchronize()
 def _describe(session: MmOwnerSession, stage: str, exc: BaseException) -> str:
    return (
        f"multimodal owner protocol failed during {stage} on group rank "
        f"{session.group.rank_in_group} (global rank "
        f"{session.group.ranks[session.group.rank_in_group]}, rids={list(session.rids)}): "
        f"{type(exc).__name__}: {exc}"
    )
 def _raise_first_error(
    statuses: List[RankStatus], cause: Optional[BaseException]
 ) -> None:
    for status in statuses:
        if status.error is not None:
            raise MmOwnerProtocolError(status.error) from cause
@@ -5,7 +5,6 @@ from typing import Callable, Dict, List, Optional, Tuple
 import torch
 from sglang.srt.managers.mm_owner_embedding import ImageSpanRequest, MmOwnerSession
 from sglang.srt.managers.schedule_batch import MultimodalDataItem
 from sglang.srt.mem_cache.multimodal_cache import EmbeddingResult, MultiModalStaticCache
 from sglang.srt.multimodal.evs import EVSEmbeddingResult
@@ -340,24 +339,43 @@ def _batch_encode_per_image_misses(
    unique_misses: Dict[Tuple[Optional[int], int], Tuple[MultimodalDataItem, int]] = {}
    hash_to_embedding: Dict[Tuple[Optional[int], int], torch.Tensor] = {}
-    # Phase 1a: collect cache misses over the unique overlapping spans
+    # Phase 1a: find overlapping items per request and collect cache misses
-    for span in _collect_image_span_requests(per_image_requests):
+    for req_info in per_image_requests:
-        cache_key = (span.hash, span.span_len)
+        chunk_start = req_info.extend_prefix_len
-        cached = embedding_cache.get_single(span.hash)
+        chunk_end = chunk_start + req_info.extend_seq_len  # exclusive
-        if cached is not None:
+        overlapping = []
-            cached_embedding = cached.embedding
+        if req_info.extend_seq_len > 0:
-            cached_token_count = _embedding_token_count(cached_embedding)
+            for idx, (item, (start, end)) in enumerate(
-            if cached_token_count == span.span_len:
+                zip(req_info.items, req_info.items_offset)
-                hash_to_embedding[cache_key] = cached_embedding
+            ):
                if end >= chunk_start and start < chunk_end:
                    overlapping.append((idx, item, start, end))
        req_info.overlapping = overlapping
        for _idx, item, start, end in overlapping:
            expected_token_count = end - start + 1
            cache_key = (item.hash, expected_token_count)
            if cache_key in hash_to_embedding:
                continue
-            _discard_mismatched_cached_embedding(
+            cached = embedding_cache.get_single(item.hash)
-                span.hash, span.span_len, cached_token_count
+            if cached is not None:
-            )
+                cached_embedding = cached.embedding
-        elif (
+                cached_token_count = _embedding_token_count(cached_embedding)
-            span.inside_chunk and span.item.can_defer_cuda_ipc_feature_reconstruction()
+                if cached_token_count == expected_token_count:
-        ):
+                    hash_to_embedding[cache_key] = cached_embedding
-            span.item.model_specific_data[BORROW_CUDA_IPC_FEATURE_KEY] = True
+                else:
-        unique_misses[cache_key] = (span.item, span.span_len)
+                    _discard_mismatched_cached_embedding(
                        item.hash, expected_token_count, cached_token_count
                    )
                    unique_misses[cache_key] = (item, expected_token_count)
            elif cache_key not in unique_misses:
                if (
                    start >= chunk_start
                    and end < chunk_end
                    and item.can_defer_cuda_ipc_feature_reconstruction()
                ):
                    item.model_specific_data[BORROW_CUDA_IPC_FEATURE_KEY] = True
                unique_misses[cache_key] = (item, expected_token_count)
    # Phase 1b: single ViT call for all unique cache misses
    if unique_misses:
@@ -394,52 +412,6 @@ def _batch_encode_per_image_misses(
    return hash_to_embedding
 def _collect_image_span_requests(
    per_image_requests: List[PerImageRequestInfo],
 ) -> List[ImageSpanRequest]:
    spans: Dict[
        Tuple[Optional[int], int],
        Tuple[MultimodalDataItem, bool, List[MultimodalDataItem]],
    ] = {}
    for req_info in per_image_requests:
        chunk_start = req_info.extend_prefix_len
        chunk_end = chunk_start + req_info.extend_seq_len  # exclusive
        overlapping = []
        if req_info.extend_seq_len > 0:
            for idx, (item, (start, end)) in enumerate(
                zip(req_info.items, req_info.items_offset)
            ):
                if end >= chunk_start and start < chunk_end:
                    overlapping.append((idx, item, start, end))
        req_info.overlapping = overlapping
        for _idx, item, start, end in overlapping:
            cache_key = (item.hash, end - start + 1)
            if cache_key in spans:
                spans[cache_key][2].append(item)
                continue
            spans[cache_key] = (item, start >= chunk_start and end < chunk_end, [])
    return [
        ImageSpanRequest(
            hash=item_hash,
            span_len=span_len,
            item=item,
            inside_chunk=inside_chunk,
            duplicates=duplicates,
        )
        for (item_hash, span_len), (item, inside_chunk, duplicates) in spans.items()
    ]
 def _owner_span_encoder(data_embedding_func: DataEmbeddingFunc, device: torch.device):
    def encode(items: List[MultimodalDataItem]):
        if not _can_skip_pre_embed_feature_move(data_embedding_func):
            _move_items_to_device(items, device)
        return data_embedding_func(items)
    return encode
 def _get_chunked_embedding_by_item(
    data_embedding_func: DataEmbeddingFunc,
    embedding_items_per_req: List[MultimodalDataItem],
@@ -565,7 +537,6 @@ def _get_chunked_prefill_embedding(
    extend_length: List[int],
    items_offset_list: List[List[Tuple[int, int]]],
    input_ids: torch.Tensor,
    mm_owner: Optional[MmOwnerSession] = None,
 ) -> tuple[torch.Tensor | None, torch.Tensor]:
    """
    Chunked prefill embedding: encode items across all requests and extract
@@ -627,22 +598,7 @@ def _get_chunked_prefill_embedding(
    # Phase 1: batch encode all per-image cache misses in ONE ViT call
    hash_to_embedding: Dict[Tuple[Optional[int], int], torch.Tensor] = {}
-    if per_image_requests and mm_owner is not None:
+    if per_image_requests:
        # The owner protocol must see every overlapping span before any local
        # cache filtering: a rank-local hit can never skip a group collective.
        span_requests = _collect_image_span_requests(per_image_requests)
        if mm_owner.engaged:
            hash_to_embedding = mm_owner.resolve(
                span_requests,
                cache=embedding_cache,
                encode=_owner_span_encoder(data_embedding_func, device),
            )
        elif span_requests:
            raise RuntimeError(
                "owner eligibility saw no image span in this chunk, but "
                f"scheduling found {len(span_requests)}"
            )
    elif per_image_requests:
        hash_to_embedding = _batch_encode_per_image_misses(
            data_embedding_func, per_image_requests, device
        )
@@ -745,7 +701,6 @@ def get_embedding_and_mask(
    prefix_length: List[int],
    extend_length: List[int],
    items_offset_list: List[List[Tuple[int, int]]],
    mm_owner: Optional[MmOwnerSession] = None,
 ) -> Tuple[torch.Tensor | None, torch.Tensor | None, torch.Tensor]:
    """
    Generate multimodal embeddings and create a mask for identifying their positions in the input sequence.
@@ -786,7 +741,6 @@ def get_embedding_and_mask(
            extend_length,
            items_offset_list,
            input_ids,
            mm_owner=mm_owner,
        )
        if embedding is None:
            return None, None, input_ids
@@ -10,7 +10,6 @@ import pickle
 import sys
 from abc import abstractmethod
 from collections import defaultdict
 from contextlib import nullcontext
 from multiprocessing import shared_memory
 from typing import Any, Dict, List, Optional, Tuple
@@ -25,7 +24,6 @@ from sglang.srt.managers.io_struct import (
    TokenizedEmbeddingReqInput,
    TokenizedGenerateReqInput,
 )
 from sglang.srt.managers.mm_owner_embedding import MmOwnerSession
 # Preserve the existing initialization import for downstream callers.
 from sglang.srt.managers.mm_schedule import (
@@ -399,7 +397,6 @@ def embed_mm_inputs(
    data_embedding_func_mapping: Dict[Modality, DataEmbeddingFunc] = None,
    placeholder_tokens: dict[Modality, List[int]] = None,
    use_deepstack: Dict[Modality, bool] = {},
    mm_owner: Optional[MmOwnerSession] = None,
 ) -> Optional[torch.Tensor]:
    """
    Embed multimodal inputs and integrate them with text token embeddings.
@@ -481,7 +478,6 @@ def embed_mm_inputs(
                prefix_length=extend_prefix_lens,
                extend_length=extend_seq_lens,
                items_offset_list=items_offsets,
                mm_owner=mm_owner,
            )
            if use_deepstack.get(modality, None) and embedding is not None:
@@ -502,12 +498,7 @@ def embed_mm_inputs(
    # filled with the hash values of the multimodal for the prefix matching in the radix attention.
    # There values are useless because their embeddings will be replaced by vision embeddings anyway.
    input_ids.clamp_(min=0, max=vocab_size - 1)
-    if mm_owner is not None:
+    input_embeds = input_embedding(input_ids)
        # The text embedding may all-reduce across TP; a rank-local failure in
        # feature preparation has to be agreed on before any rank enters it.
        mm_owner.features_ready()
    with mm_owner.uncaptured() if mm_owner is not None else nullcontext():
        input_embeds = input_embedding(input_ids)
    # deepstack embedding
    if use_deepstack:
@@ -534,9 +525,7 @@ def embed_mm_inputs(
        _scatter_mm_embedding(dest=input_embeds, mask=mask, src=embedding)
        if use_deepstack.get(modality, None):
            _scatter_mm_embedding(
-                dest=input_deepstack_embeds,
+                dest=input_deepstack_embeds, mask=mask, src=deepstack_embeddings[i]
                mask=mask,
                src=deepstack_embeddings[i],
            )
    return input_embeds, other_info
@@ -1019,15 +1019,6 @@ class PrefillAdder:
            else AddReqResult.CONTINUE
        )
    def can_share_extend_batch(self, req: Req) -> bool:
        # Token embedding overrides embed the batch's raw input_ids before the
        # model runs, and that lookup cannot index multimodal placeholder hash IDs.
        if req.positional_embed_overrides is not None:
            return all(r.multimodal_inputs is None for r in self.can_run_list)
        if req.multimodal_inputs is not None:
            return all(r.positional_embed_overrides is None for r in self.can_run_list)
        return True
    def add_chunked_req(self, req: Req):
        if self.dllm_config is not None:
            _rem_tokens = self._get_dllm_remain_tokens()
@@ -2097,13 +2097,9 @@ class Scheduler(
                vmm_errors = self._materialize_cuda_vmm_inputs(recv_req)
            # Skip health check when server is busy — ongoing requests already carry health info.
-            # NOTE: the admit/skip decision must be identical on every CP/TP rank.
+            if is_health_check_generate_req(recv_req) and not self.is_fully_idle(
-            # is_fully_idle() includes rank-local hicache drain queues, which diverge
+                for_health_check=True
-            # across ranks right after activity; a divergent decision lets one rank
+            ):
            # dispatch the health-check generate while others piggyback-skip, breaking
            # collective ordering (deadlock: one rank blocks in the hicache drain
            # all_reduce while another waits in the CP request broadcast).
            if is_health_check_generate_req(recv_req) and not self.is_sched_idle_cp_symmetric():
                self.return_health_check_ipcs.append(
                    getattr(recv_req, "http_worker_ipc", None)
                )
@@ -3944,8 +3940,6 @@ class Scheduler(
        for req in self.waiting_queue:
            if self.enable_lora and not self.can_schedule_lora_req(req, running_loras):
                continue
            if not adder.can_share_extend_batch(req):
                break
            running_bs = len(running_batch.reqs)
            candidate_beam_width = (
@@ -4986,31 +4980,6 @@ class Scheduler(
        else:
            self.metrics_reporter.record_scheduler_active()
    def is_sched_idle_cp_symmetric(self) -> bool:
        """Idle check using only state that is identical across CP/TP ranks.
        Request/batch/queue state is collectively maintained (requests arrive
        via broadcast, batches are collectively scheduled), so every rank
        computes the same result. Rank-local hicache drain and disagg transfer
        queues are deliberately excluded: those are exactly the terms that
        diverge across ranks and caused the CP health-check deadlock
        (hicache drain all_reduce vs CP request broadcast cross-collective
        wait, seen on cp2/cp4 + hicache L3 right after router health checks).
        Used only for health-check admission; all other idle logic keeps using
        is_fully_idle().
        """
        return (
            self.running_batch.is_empty()
            and self.chunked_req is None
            and not self.dllm_manager.any_staging_reqs()
            and (self.last_batch is None or self.last_batch.is_empty())
            and (not self.enable_overlap or len(self.result_queue) == 0)
            and self._pp_microbatches_drained()
            and len(self.waiting_queue) == 0
            and len(self.grammar_manager.grammar_queue) == 0
        )
    def is_fully_idle(self, for_health_check=False) -> bool:
        # Health check piggybacks on running requests in process_output.
        # Only running_batch + waiting_queue guarantee active GPU processing;
@@ -1279,16 +1279,6 @@ class TokenizerManager(TokenizerControlMixin, TokenizerManagerScoreMixin):
                raise ValueError(
                    "encoder SWA replay cannot return cached prompt logprobs"
                )
        requests_embed_overrides = obj.positional_embed_overrides is not None or (
            isinstance(obj, EmbeddingReqInput)
            and obj.embed_overrides is not None
            and obj.embed_override_token_id is not None
        )
        if requests_embed_overrides and obj.contains_mm_input():
            raise ValueError(
                "embedding overrides cannot be combined with image, video, or audio "
                "inputs"
            )
        _max_req_len = self.context_len
        input_token_num = len(input_ids) if input_ids is not None else 0
        input_token_num += self.num_reserved_tokens
@@ -1646,7 +1646,6 @@ class ModelRunner:
            forward_batch.replace_embeds is not None
            and forward_batch.replace_positions is not None
        ):
            misc_utils.validate_replace_embeds_batch(forward_batch)
            # Token embedding overrides: get base embeddings, scatter replacements
            if "input_embeds" not in kwargs:
                embed_layer = self.model.get_input_embeddings()
@@ -18,7 +18,6 @@ from sglang.srt.server_args import CHUNKED_PREFIX_CACHE_SUPPORTED_ATTENTION_BACK
 if TYPE_CHECKING:
    from sglang.srt.configs.model_config import ModelConfig
    from sglang.srt.model_executor.forward_batch_info import ForwardBatch
 logger = logging.getLogger(__name__)
@@ -106,24 +105,3 @@ def resolve_pp_proxy_dspark_hidden_size(
    if isinstance(model, _SupportsDSparkPPProxy):
        return model.get_pp_proxy_dspark_hidden_size()
    return 0
 def validate_replace_embeds_batch(forward_batch: ForwardBatch) -> None:
    if forward_batch.mm_inputs is None:
        return
    for mm_inputs, prefix_len, extend_len in zip(
        forward_batch.mm_inputs,
        forward_batch.extend_prefix_lens_cpu,
        forward_batch.extend_seq_lens_cpu,
    ):
        if mm_inputs is None:
            continue
        chunk_end = prefix_len + extend_len
        for item in mm_inputs.mm_items:
            for start, end in item.offsets or ():
                if start < chunk_end and end >= prefix_len:
                    # Placeholder rows carry hash IDs the base embedding lookup cannot index.
                    raise ValueError(
                        "Token embedding overrides cannot share an extend batch with "
                        "multimodal placeholders"
                    )
@@ -387,13 +387,12 @@ class EagerRunner(BaseRunner):
        input_ids = forward_batch.input_ids
        input_embeds = kwargs.get("input_embeds")
-        if hasattr(model, "prepare_model_inputs"):
+        # Multimodal spans must be embedded in global token order, before CP
-            # Multimodal offsets are request-global, so the merge and the
+        # slicing. The model may also normalize image hash IDs for its router.
-            # placeholder-ID remap must see the full extend layout first.
+        prepare_inputs = getattr(model, "prepare_language_model_inputs", None)
-            input_ids, input_embeds = model.prepare_model_inputs(
+        if prepare_inputs is not None:
-                input_ids=input_ids,
+            input_ids, input_embeds = prepare_inputs(
-                forward_batch=forward_batch,
+                input_ids, forward_batch, input_embeds
                input_embeds=input_embeds,
            )
        if input_embeds is None:
            input_embeds = model.get_input_embeddings()(input_ids)
@@ -74,7 +74,6 @@ from sglang.srt.layers.communicator_dsa_cp import (
    dsa_cp_gather_hidden_states,
    dsa_cp_reduce_scatter_hidden_states,
 )
 from sglang.srt.layers.cp.base import is_zigzag
 from sglang.srt.layers.cp.cp_decode_attn_tp import get_cp_decode_attn_tp_ctx
 from sglang.srt.layers.cp.utils import (
    cp_gather_full_sequence_states,
@@ -121,11 +120,6 @@ from sglang.srt.layers.quantization.mxfp8_input import Mxfp8SwizzledInput
 from sglang.srt.layers.rotary_embedding import get_rope_wrapper
 from sglang.srt.layers.utils import PPMissingLayer, get_layer_id
 from sglang.srt.layers.vocab_parallel_embedding import VocabParallelEmbedding
 from sglang.srt.managers.mm_owner_embedding import (
    MmOwnerSession,
    has_owner_span_work,
    select_owner_group,
 )
 from sglang.srt.managers.mm_utils import (
    MultiModalityDataPaddingPatternMultimodalTokens,
    embed_mm_inputs,
@@ -4903,18 +4897,14 @@ class DeepseekV4ForCausalLM(nn.Module):
            and not getattr(config, "language_model_only", False)
        ):
            if (
-                get_parallel().pp_group.world_size != 1
+                get_parallel().attn_cp_size != 1
                or get_pp_group().world_size != 1
                or not _v41_vision_a2a_supported()
            ):
                raise ValueError(
-                    "V4.1 vision supports TP/EP/DP without PP; "
+                    "V4.1 vision supports TP/EP/DP without CP or PP; "
                    "MoE A2A is supported only with MegaMoE on a PD decode node"
                )
            if get_parallel().attn_cp_size != 1 and (_is_npu or is_zigzag()):
                raise ValueError(
                    "V4.1 vision context parallelism requires the CUDA interleave "
                    "strategy; NPU and zigzag CP are not supported yet"
                )
            args = SimpleNamespace(**vars(config), dim=config.hidden_size)
            self.vision = ViT(args)
@@ -4922,11 +4912,6 @@ class DeepseekV4ForCausalLM(nn.Module):
            self.image_start = nn.Parameter(torch.empty(config.hidden_size))
            self.image_end = nn.Parameter(torch.empty(config.hidden_size))
            self.image_newline = nn.Parameter(torch.empty(config.hidden_size))
        self.mm_owner_group = (
            select_owner_group(get_parallel())
            if self.vision is not None and _is_cuda
            else None
        )
        self.model = DeepseekV4Model(
            config, quant_config, prefix=add_prefix("model", prefix)
        )
@@ -5061,42 +5046,7 @@ class DeepseekV4ForCausalLM(nn.Module):
            spans.append(span)
        return spans
-    def _image_span_signature(self, item, span_len: int):
+    def _prepare_mm_embeddings(self, input_ids, forward_batch):
        h, w = int(item.n_vit_h), int(item.n_vit_w)
        r = self.config.vision_downsample_ratio
        expected = len(image_token_types((h + r - 1) // r, (w + r - 1) // r))
        if expected != span_len:
            raise ValueError(
                f"image grid {(h, w)} yields {expected} span tokens, "
                f"placeholder has {span_len}"
            )
        plan = item.model_specific_data.get(GPU_PLAN_KEY)
        feature = item.feature
        return (
            h,
            w,
            tuple(feature.shape) if isinstance(feature, torch.Tensor) else None,
            None if plan is None else tuple(sorted(plan.items())),
        )
    def _mm_owner_session(self, forward_batch) -> Optional[MmOwnerSession]:
        if self.mm_owner_group is None:
            return None
        return MmOwnerSession(
            group=self.mm_owner_group,
            device=self.image_start.device,
            dtype=self.image_start.dtype,
            width=self.config.hidden_size,
            rids=list(forward_batch.rids or ()),
            signature=self._image_span_signature,
            engaged=has_owner_span_work(
                forward_batch.mm_inputs,
                forward_batch.extend_prefix_lens_cpu,
                forward_batch.extend_seq_lens_cpu,
            ),
        )
    def _prepare_mm_embeddings(self, input_ids, forward_batch, mm_owner):
        # Keep scheduler hash IDs intact: the shared embedder clamps its input in place.
        input_embeds, _ = embed_mm_inputs(
            mm_inputs_list=[
@@ -5108,7 +5058,6 @@ class DeepseekV4ForCausalLM(nn.Module):
            input_ids=input_ids.clone(),
            input_embedding=self.get_input_embeddings(),
            multimodal_model=self,
            mm_owner=mm_owner,
        )
        forward_batch.mm_input_embeds = input_embeds
        return input_embeds
@@ -5116,41 +5065,6 @@ class DeepseekV4ForCausalLM(nn.Module):
    def get_input_embeddings(self) -> nn.Module:
        return self.model.get_input_embeddings()
    def prepare_model_inputs(
        self,
        input_ids: torch.Tensor,
        forward_batch: ForwardBatch,
        input_embeds: Optional[torch.Tensor],
    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
        if self.vision is None:
            return input_ids, input_embeds
        has_images = (
            not forward_batch.forward_mode.is_decode()
            and not forward_batch.forward_mode.is_target_verify()
            and forward_batch.mm_inputs is not None
            and any(x is not None for x in forward_batch.mm_inputs)
        )
        if has_images and input_embeds is not None:
            raise ValueError("Cannot combine input_embeds and image inputs")
        mm_owner = self._mm_owner_session(forward_batch) if has_images else None
        # Peers may only enter the body or the CP shard once every rank has
        # finished all of its fallible input preparation, the remap included.
        with mm_owner.fence() if mm_owner is not None else nullcontext():
            if has_images:
                input_embeds = self._prepare_mm_embeddings(
                    input_ids, forward_batch, mm_owner
                )
            if not (
                forward_batch.forward_mode.is_decode_or_idle()
                or forward_batch.forward_mode.is_target_verify()
            ):
                # Decode/verify IDs are already vocabulary IDs; remap prompt image
                # hashes for Engram and routing.
                input_ids = input_ids.masked_fill(
                    input_ids >= MM_PAD_SHIFT_VALUE, self.config.image_token_id
                )
        return input_ids, input_embeds
    def set_dspark_layers_to_capture(self, layer_ids: List[int]) -> None:
        if not self.pp_group.is_last_rank:
            return
@@ -5201,11 +5115,31 @@ class DeepseekV4ForCausalLM(nn.Module):
        input_ids: torch.Tensor,
        forward_batch: ForwardBatch,
        input_embeds: Optional[torch.Tensor] = None,
-        pp_proxy_tensors: Optional[PPProxyTensors] = None,
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
-    ) -> torch.Tensor:
+        """Prepare full-sequence image embeddings and model IDs before CP splits.
-        input_ids, input_embeds = self.prepare_model_inputs(
+
-            input_ids=input_ids, forward_batch=forward_batch, input_embeds=input_embeds
+        Scheduler hash IDs stay intact for multimodal cache keys; the language
-        )
+        model uses image_token_id for Engram masking and visual MoE routing.
        """
        if (
            getattr(self, "vision", None) is not None
            and not forward_batch.forward_mode.is_decode()
            and not forward_batch.forward_mode.is_target_verify()
            and forward_batch.mm_inputs is not None
            and any(x is not None for x in forward_batch.mm_inputs)
        ):
            if input_embeds is not None:
                raise ValueError("Cannot combine input_embeds and image inputs")
            input_embeds = self._prepare_mm_embeddings(input_ids, forward_batch)
        if getattr(self, "vision", None) is not None and not (
            forward_batch.forward_mode.is_decode_or_idle()
            or forward_batch.forward_mode.is_target_verify()
        ):
            # Decode/verify IDs are already vocabulary IDs; remap prompt image
            # hashes for Engram and routing.
            input_ids = input_ids.masked_fill(
                input_ids >= MM_PAD_SHIFT_VALUE, self.config.image_token_id
            )
        return input_ids, input_embeds
@@ -222,7 +222,6 @@ class DeepseekV4ForCausalLMNextN(DeepseekV4ForCausalLM):
        self.quant_config = quant_config
        self.wo_a_fp8 = wo_a_fp8_gemm_enabled(quant_config)
        self.determine_num_fused_shared_experts()
        self.vision = None
        self.model = DeepseekV4ModelNextN(
            config, quant_config, prefix=add_prefix("model", prefix)
@@ -9,7 +9,6 @@ Covers:
 """
 import unittest
 from types import SimpleNamespace
 from unittest.mock import AsyncMock, MagicMock
 import torch
@@ -18,16 +17,10 @@ from sglang.srt.constants import MIS_DELIMITER_TOKEN_ID
 from sglang.srt.entrypoints.openai.utils import convert_embeds_to_tensors
 from sglang.srt.managers.embed_types import PositionalEmbeds
 from sglang.srt.managers.io_struct import EmbeddingReqInput, GenerateReqInput
 from sglang.srt.managers.schedule_batch import (
    Modality,
    MultimodalDataItem,
    MultimodalInputs,
 )
 from sglang.srt.managers.tokenizer_manager import TokenizerManager
 from sglang.srt.managers.tokenizer_manager_score_mixin import (
    TokenizerManagerScoreMixin,
 )
 from sglang.srt.model_executor.model_runner import ModelRunner
 from sglang.srt.runtime_context import publish, reset_context
 from sglang.srt.server_args import ServerArgs
 from sglang.test.ci.ci_register import register_cpu_ci
@@ -649,87 +642,5 @@ class TestScoreRequestValidation(CustomTestCase):
            )
 class TestEmbedOverridesRejectMultimodal(CustomTestCase):
    def setUp(self):
        reset_context()
        self.addCleanup(reset_context)
        publish(ServerArgs(model_path="dummy"), role="tokenizer")
        self.manager = TokenizerManager.__new__(TokenizerManager)
        self.manager.context_len = 128
        self.manager.num_reserved_tokens = 0
        self.manager.allow_auto_truncate = False
        self.manager.validate_total_tokens = False
        self.manager.is_generation = True
    def _request(self, **fields):
        return GenerateReqInput(
            input_ids=[10, 50, 20],
            sampling_params={},
            positional_embed_overrides=PositionalEmbeds(embeds=[_vec()], positions=[1]),
            **fields,
        )
    def test_request_with_image_is_rejected(self):
        req = self._request(image_data=["image.png"])
        with self.assertRaisesRegex(ValueError, "overrides cannot be combined"):
            self.manager._validate_one_request(req, req.input_ids)
        text_only = self._request()
        self.manager._validate_one_request(text_only, text_only.input_ids)
    def test_unresolved_embedding_overrides_with_image_are_rejected(self):
        """EmbeddingReqInput resolves embed_overrides only after validation, so
        the unresolved form must be caught at admission too."""
        self.manager.is_generation = False
        req = EmbeddingReqInput(
            input_ids=[10, 50, 20],
            sampling_params={},
            embed_override_token_id=50,
            embed_overrides=[_vec()],
            image_data=["image.png"],
        )
        with self.assertRaisesRegex(ValueError, "overrides cannot be combined"):
            self.manager._validate_one_request(req, req.input_ids)
        req.image_data = None
        self.manager._validate_one_request(req, req.input_ids)
    def test_mixed_extend_batch_is_rejected_before_embedding_lookup(self):
        """Placeholder rows hold hash IDs, so the base lookup must never run
        on a batch whose chunk also covers multimodal placeholders."""
        embed_layer = MagicMock(
            side_effect=AssertionError("embedding lookup must not run")
        )
        runner = SimpleNamespace(
            _pp_kwargs=lambda pp_proxy_tensors: {},
            model=SimpleNamespace(get_input_embeddings=lambda: embed_layer),
            is_generation=True,
        )
        image = MultimodalDataItem(
            modality=Modality.IMAGE, feature=torch.zeros(1), offsets=[(0, 1)]
        )
        image.set_hash(1234)
        forward_batch = SimpleNamespace(
            input_embeds=None,
            input_ids=torch.tensor([1, 2, image.pad_value, image.pad_value]),
            replace_embeds=torch.full((1, HIDDEN_DIM), 5.0),
            replace_positions=torch.tensor([0]),
            mm_inputs=[None, MultimodalInputs(mm_items=[image])],
            extend_prefix_lens_cpu=[0, 0],
            extend_seq_lens_cpu=[2, 2],
        )
        with self.assertRaisesRegex(ValueError, "cannot share an extend batch"):
            ModelRunner._extend_forward_kwargs(runner, forward_batch, None)
        embed_layer.assert_not_called()
        # A decoding image request in a mixed chunk has no placeholder rows here.
        forward_batch.input_ids = torch.tensor([1, 2, 3])
        forward_batch.extend_prefix_lens_cpu = [0, 5]
        forward_batch.extend_seq_lens_cpu = [2, 1]
        embed_layer.side_effect = None
        embed_layer.return_value = torch.zeros(3, HIDDEN_DIM)
        kwargs = ModelRunner._extend_forward_kwargs(runner, forward_batch, None)
        self.assertTrue(torch.equal(kwargs["input_embeds"][0], _vec(5.0)))
 if __name__ == "__main__":
    unittest.main()
@@ -28,13 +28,7 @@ from sglang.srt.runtime_context import get_context
 from sglang.srt.server_args import ServerArgs, set_global_server_args_for_scheduler
 from sglang.srt.utils.common import Range
 from sglang.test.ci.ci_register import register_cpu_ci
-from sglang.test.test_utils import CustomTestCase, maybe_stub_sgl_kernel
+from sglang.test.test_utils import CustomTestCase
 maybe_stub_sgl_kernel()
 import sglang.srt.managers.scheduler as scheduler_module
 from sglang.srt.disaggregation.utils import DisaggregationMode
 from sglang.srt.managers.scheduler import Scheduler
 register_cpu_ci(est_time=11, suite="base-a-test-cpu")
@@ -302,139 +296,6 @@ class TestPrefillAdder(CustomTestCase):
        )
        self.assertEqual(adder.can_run_list, [first])
    def test_embed_override_and_multimodal_requests_never_share_a_batch(self):
        def tagged(rid, *, multimodal=False, overrides=False):
            req = self.create_shared_req(rid)
            req.multimodal_inputs = object() if multimodal else None
            req.positional_embed_overrides = object() if overrides else None
            return req
        for first, second in (
            (tagged("image", multimodal=True), tagged("override", overrides=True)),
            (tagged("override", overrides=True), tagged("image", multimodal=True)),
        ):
            with self.subTest(first=first.rid):
                adder = self.create_shared_adder()
                self.assertTrue(adder.can_share_extend_batch(first))
                adder.add_one_req(
                    first, has_chunked_req=False, truncation_align_size=None
                )
                self.assertEqual(adder.can_run_list, [first])
                self.assertFalse(adder.can_share_extend_batch(second))
                self.assertTrue(adder.can_share_extend_batch(tagged("text")))
        adder = self.create_shared_adder()
        chunked = tagged("chunked-image", multimodal=True)
        chunked.full_untruncated_fill_ids = list(range(64))
        self.assertIs(adder.add_chunked_req(chunked), chunked)
        self.assertFalse(
            adder.can_share_extend_batch(tagged("override", overrides=True))
        )
    def create_admission_scheduler(self, *, chunked_req) -> Scheduler:
        allocator = self.create_token_allocator(available_size=4096)
        allocator.page_size = 1
        self.mock_tree_cache.supports_mamba.return_value = False
        self.mock_tree_cache.is_tree_cache.return_value = False
        self.mock_tree_cache.supports_fast_match_prefix.return_value = False
        self.mock_tree_cache.storage_prefetch_retries = None
        scheduler = Scheduler.__new__(Scheduler)
        scheduler.grammar_manager = SimpleNamespace(has_waiting_grammars=lambda: False)
        scheduler.enable_priority_preemption = False
        scheduler.enable_priority_scheduling = False
        scheduler.is_hybrid_swa = False
        scheduler.min_free_slots_delayer = None
        scheduler.get_num_allocatable_reqs = lambda *args, **kwargs: 64
        scheduler.policy = SchedulePolicy(
            policy="fcfs",
            tree_cache=self.mock_tree_cache,
            enable_hierarchical_cache=False,
            enable_priority_scheduling=False,
            schedule_low_priority_values_first=False,
        )
        scheduler.processed_tokens_counter = 0
        scheduler.chunked_prefill_size = 16
        scheduler.dynamic_chunk_sizer = None
        scheduler.tp_worker = SimpleNamespace(
            model_runner=SimpleNamespace(attn_backend=object(), prefill_aware_swa=False)
        )
        scheduler.page_size = 1
        scheduler.tree_cache = self.mock_tree_cache
        scheduler.token_to_kv_pool_allocator = allocator
        scheduler.new_token_ratio_tracker = SimpleNamespace(current=1.0)
        scheduler.max_prefill_tokens = 16384
        scheduler.is_mixed_chunk = False
        scheduler.priority_scheduling_preemption_threshold = 0
        scheduler.max_prefill_bs = 64
        scheduler.max_running_requests = 64
        scheduler.dllm_config = None
        scheduler.enable_lora = False
        scheduler.req_to_token_pool = SimpleNamespace()
        scheduler.disaggregation_mode = DisaggregationMode.NULL
        scheduler.enable_hicache_storage = False
        scheduler.enable_hierarchical_cache = False
        scheduler.enable_unified_cache_external_linker = False
        scheduler.truncation_align_size = None
        scheduler.model_config = None
        scheduler.enable_overlap = False
        scheduler.spec_algorithm = None
        scheduler.load_inquirer = MagicMock()
        scheduler.chunked_req = chunked_req
        scheduler.waiting_queue = []
        return scheduler
    def run_admission_pass(self, scheduler: Scheduler) -> list:
        running_batch = self.create_running_batch()
        running_batch.batch_is_full = False
        with (
            patch.object(scheduler_module, "ScheduleBatch") as schedule_batch,
            patch.object(scheduler_module, "PrefillStats"),
            patch.object(scheduler_module, "set_time_batch"),
        ):
            new_batch, _ = scheduler._get_new_batch_prefill_raw(None, running_batch)
        if new_batch is None:
            return []
        admitted = list(schedule_batch.init_new.call_args.args[0])
        for req in admitted:
            req.prefix_indices = list(range(req.extend_range.end))
        return admitted
    def test_fcfs_admits_override_request_once_image_continuation_drains(self):
        """An override request at the queue head must be admitted once the image
        chunk ahead of it drains, even while more image requests keep arriving."""
        def tagged(rid, length, *, multimodal=False, overrides=False):
            req = self.create_shared_req(rid)
            req.origin_input_ids = list(range(length))
            req.full_untruncated_fill_ids = list(range(length))
            req.multimodal_inputs = object() if multimodal else None
            req.positional_embed_overrides = object() if overrides else None
            req.beam_group = None
            req.inflight_middle_chunks = 0
            return req
        continuation = tagged("image-continuation", 20, multimodal=True)
        continuation.prefix_indices = list(range(16))
        scheduler = self.create_admission_scheduler(chunked_req=continuation)
        override = tagged("override", 4, overrides=True)
        scheduler.waiting_queue = [override]
        admitted_at = None
        for pass_index in range(6):
            scheduler.waiting_queue.append(
                tagged(f"image-{pass_index}", 16, multimodal=True)
            )
            admitted = self.run_admission_pass(scheduler)
            self.assertFalse(
                any(r.multimodal_inputs is not None for r in admitted)
                and any(r.positional_embed_overrides is not None for r in admitted)
            )
            if any(r is override for r in admitted):
                admitted_at = pass_index
                break
        self.assertIsNotNone(admitted_at)
        self.assertNotIn(override, scheduler.waiting_queue)
    def test_shared_admission_rechecks_after_prefix_lock(self):
        adder = self.create_shared_adder()
        self.assertIsNotNone(adder.token_to_kv_pool_allocator.alloc(24))
@@ -1,261 +0,0 @@
 """Vision inputs under prefill CP merge on the full extend layout before the shard."""
 import unittest
 from contextlib import contextmanager
 from types import SimpleNamespace
 from unittest.mock import patch
 import torch
 from torch import nn
 from sglang.srt.layers.cp.base import init_cp_strategy
 from sglang.srt.layers.cp.utils import prepare_cp_forward
 from sglang.srt.managers import mm_schedule
 from sglang.srt.managers.schedule_batch import (
    Modality,
    MultimodalDataItem,
    MultimodalInputs,
 )
 from sglang.srt.model_executor.forward_batch_info import ForwardMode
 from sglang.srt.model_executor.runner.eager_runner import EagerRunner
 from sglang.srt.models.deepseek_v4 import DeepseekV4ForCausalLM
 from sglang.srt.runtime_context import get_parallel
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 register_cpu_ci(est_time=15, suite="base-a-test-cpu")
 HIDDEN = 8
 VOCAB = 64
 IMAGE_TOKEN_ID = 7
 CP_SIZE = 4
 # (prefix_len, extend_len) per request. Request 1 carries one image whose span
 # [2, 8] starts inside its prefix, so only span rows 1..6 land in this chunk.
 CHUNKS = [(0, 7), (3, 9), (1, 5)]
 IMAGE_OFFSET = (2, 8)
 IMAGE_HASH = 12345
 NUM_TOKENS = sum(extend_len for _, extend_len in CHUNKS)
 # 21 tokens over 4 ranks give logical [6, 5, 5, 5], padded to the CP alignment.
 PHYSICAL_ROWS = 8
 IMAGE_ROWS = torch.arange(7, 13)
 POSITIONS = torch.cat([torch.arange(p, p + n) for p, n in CHUNKS])
 def _image_span(item: MultimodalDataItem) -> torch.Tensor:
    start, end = item.offsets[0]
    rows = end - start + 1
    return torch.arange(rows * HIDDEN, dtype=torch.float32).view(rows, HIDDEN) + 100.0
 def _pad(x: torch.Tensor) -> torch.Tensor:
    return torch.cat([x, x.new_zeros(PHYSICAL_ROWS - x.shape[0], *x.shape[1:])])
 class _RecordingBody:
    def __init__(self, embed: nn.Embedding):
        self.embed = embed
        self.calls = []
    def get_input_embeddings(self):
        return self.embed
    def __call__(self, input_ids, positions, forward_batch, input_embeds=None):
        self.calls.append(
            SimpleNamespace(
                input_ids=input_ids,
                positions=positions,
                input_embeds=input_embeds,
                input_ids_global=forward_batch.input_ids_global,
            )
        )
        return input_embeds, input_embeds
 class _VisionStub(DeepseekV4ForCausalLM):
    def __init__(self, embed: nn.Embedding):
        nn.Module.__init__(self)
        self.config = SimpleNamespace(image_token_id=IMAGE_TOKEN_ID)
        self.vision = object()
        self.tp_size = 1
        self.mm_owner_group = None
        self.model = _RecordingBody(embed)
        self.pp_group = SimpleNamespace(is_last_rank=True)
        self.lm_head = object()
        self.capture_aux_hidden_states = False
        self.logits_calls = []
    def get_image_feature(self, items):
        return [_image_span(item) for item in items]
    def logits_processor(
        self,
        input_ids,
        hidden_states,
        lm_head,
        logits_metadata,
        aux_hidden_states=None,
        hidden_states_before_norm=None,
    ):
        self.logits_calls.append(
            SimpleNamespace(
                input_ids=input_ids,
                hidden_states=hidden_states,
                logits_metadata=logits_metadata,
                hidden_states_before_norm=hidden_states_before_norm,
            )
        )
        return object()
 def _build_batch():
    item = MultimodalDataItem(
        modality=Modality.IMAGE, feature=torch.zeros(1), offsets=[IMAGE_OFFSET]
    )
    item.set_hash(IMAGE_HASH)
    ids = list(range(10, 17))
    ids += [item.pad_value] * len(IMAGE_ROWS) + [20, 21, 22]
    ids += list(range(30, 35))
    forward_batch = SimpleNamespace(
        forward_mode=ForwardMode.EXTEND,
        mm_inputs=[
            MultimodalInputs(mm_items=[]),
            MultimodalInputs(mm_items=[item], im_token_id=IMAGE_TOKEN_ID),
            None,
        ],
        extend_prefix_lens_cpu=[prefix for prefix, _ in CHUNKS],
        extend_seq_lens_cpu=[extend_len for _, extend_len in CHUNKS],
        seq_lens_cpu=[prefix + extend_len for prefix, extend_len in CHUNKS],
        input_ids=torch.tensor(ids, dtype=torch.long),
        positions=POSITIONS.clone(),
        mm_input_embeds=None,
        attn_cp_metadata=None,
        global_num_tokens_cpu=None,
        out_cache_loc=None,
        input_ids_global=torch.zeros(1, dtype=torch.long),
    )
    return forward_batch, item
 def _expected_embeds(embed, scheduler_ids, item):
    with torch.no_grad():
        full = embed(scheduler_ids.clamp(max=VOCAB - 1))
    full[IMAGE_ROWS] = _image_span(item)[1:7]
    return full
 def _canonical(scheduler_ids):
    canonical = scheduler_ids.clone()
    canonical[IMAGE_ROWS] = IMAGE_TOKEN_ID
    return canonical
 class TestDeepseekV41VisionPrefillCPInputs(CustomTestCase):
    def setUp(self):
        mm_schedule.init_mm_embedding_cache(1 << 20)
        init_cp_strategy(
            enable_prefill_cp=True, cp_size=CP_SIZE, cp_strategy="interleave"
        )
        torch.manual_seed(0)
        self.embed = nn.Embedding(VOCAB, HIDDEN)
        self.model = _VisionStub(self.embed)
    def tearDown(self):
        init_cp_strategy(enable_prefill_cp=False, cp_size=1, cp_strategy="interleave")
    @contextmanager
    def _cp_collectives(self, full: torch.Tensor, rank: int):
        def all_gather(output, input_tensor):
            # Peers contribute their expected shards; this rank's rows come from
            # what the runner actually handed to the collective.
            output.zero_()
            for peer in range(CP_SIZE):
                rows = full[peer::CP_SIZE]
                output[peer * PHYSICAL_ROWS : peer * PHYSICAL_ROWS + rows.shape[0]] = (
                    rows
                )
            output[rank * PHYSICAL_ROWS : (rank + 1) * PHYSICAL_ROWS] = input_tensor
        with (
            patch("torch.cuda.current_stream", return_value=None),
            patch(
                "sglang.srt.layers.cp.interleave.attn_cp_all_gather_into_tensor",
                side_effect=all_gather,
            ),
            patch(
                "sglang.srt.layers.cp.interleave.is_allocation_symmetric",
                return_value=False,
            ),
            patch(
                "sglang.srt.layers.cp.interleave.use_symmetric_memory",
                return_value=torch.no_grad(),
            ),
        ):
            yield
    def _prepare(self, forward_batch, input_embeds=None):
        with torch.no_grad():
            return self.model.prepare_model_inputs(
                input_ids=forward_batch.input_ids,
                forward_batch=forward_batch,
                input_embeds=input_embeds,
            )
    def test_cp_runner_merges_before_shard(self):
        runner = EagerRunner.__new__(EagerRunner)
        runner.model_runner = SimpleNamespace(model=self.model)
        padded = torch.zeros(CP_SIZE * PHYSICAL_ROWS, dtype=torch.long)
        for rank in range(CP_SIZE):
            forward_batch, item = _build_batch()
            routing_sentinel = forward_batch.input_ids_global
            scheduler_ids = forward_batch.input_ids.clone()
            canonical = _canonical(scheduler_ids)
            full = _expected_embeds(self.embed, scheduler_ids, item)
            padded[:NUM_TOKENS] = canonical
            rank_major_ids = padded.view(-1, CP_SIZE).T.flatten()
            self.model.model.calls.clear()
            self.model.logits_calls.clear()
            with (
                get_parallel().override(
                    attn_cp_rank=rank, attn_cp_size=CP_SIZE, attn_cp_group=object()
                ),
                self._cp_collectives(full, rank),
                torch.no_grad(),
            ):
                prepare_cp_forward(forward_batch)
                runner._execute_extend_cp(forward_batch, {})
            with self.subTest(rank=rank):
                metadata = forward_batch.attn_cp_metadata
                self.assertEqual(metadata.per_rank_actual_token, [PHYSICAL_ROWS] * 4)
                (body,) = self.model.model.calls
                self.assertTrue(
                    torch.equal(body.input_ids, _pad(canonical[rank::CP_SIZE]))
                )
                self.assertTrue(
                    torch.equal(body.positions, _pad(POSITIONS[rank::CP_SIZE]))
                )
                self.assertTrue(
                    torch.equal(body.input_embeds, _pad(full[rank::CP_SIZE]))
                )
                self.assertTrue(torch.equal(body.input_ids_global, rank_major_ids))
                (logits,) = self.model.logits_calls
                self.assertTrue(torch.equal(logits.input_ids, canonical))
                self.assertTrue(torch.equal(logits.hidden_states, full))
                self.assertTrue(torch.equal(logits.hidden_states_before_norm, full))
                self.assertIs(logits.logits_metadata, forward_batch)
                self.assertTrue(torch.equal(forward_batch.mm_input_embeds, full))
                self.assertTrue(torch.equal(forward_batch.input_ids, scheduler_ids))
                self.assertIs(forward_batch.input_ids_global, routing_sentinel)
    def test_external_embeddings_with_images_are_rejected(self):
        forward_batch, _ = _build_batch()
        with self.assertRaisesRegex(ValueError, "Cannot combine"):
            self._prepare(forward_batch, input_embeds=torch.zeros(NUM_TOKENS, HIDDEN))
 if __name__ == "__main__":
    unittest.main()
@@ -29,7 +29,6 @@ from sglang.srt.arg_groups.cuda_graph_hook import (
    finalize_cuda_graph_prefill_max_context,
    handle_cuda_graph_config,
 )
 from sglang.srt.arg_groups.deepseek_v4_hook import validate_deepseek_v41_features
 from sglang.srt.arg_groups.hicache_hook import (
    handle_hicache,
    handle_hicache_ratio_default,
@@ -46,7 +45,6 @@ from sglang.srt.arg_groups.kv_cache_hook import (
 )
 from sglang.srt.arg_groups.mamba_hook import handle_mamba_backend
 from sglang.srt.arg_groups.memory_hook import handle_gpu_memory_settings
 from sglang.srt.arg_groups.model_hook import handle_model_specific_adjustments
 from sglang.srt.arg_groups.model_path_hook import handle_load_format
 from sglang.srt.arg_groups.moe_hook import (
    handle_a2a_moe,
@@ -4071,86 +4069,5 @@ class TestLazyReexports(CustomTestCase):
            server_args_module.NotAThing
 class TestDeepseekV41VisionPrefillCPArgs(CustomTestCase):
    def _args(
        self,
        *,
        vision_n_layers=2,
        prefill_backend=Backend.DISABLED,
        lock_prefill_backend=False,
        **overrides,
    ):
        fields = dict(
            model_path="dummy",
            enable_prefill_cp=True,
            cp_strategy="interleave",
            tp_size=2,
        )
        fields.update(overrides)
        server_args = ServerArgs(**fields)
        server_args._model_config = SimpleNamespace(
            hf_config=SimpleNamespace(
                architectures=["DeepseekV4ForCausalLM"],
                model_type="deepseek_v41",
                vision_n_layers=vision_n_layers,
            ),
            nvfp4_moe_meta=None,
            is_fp4_experts=False,
        )
        # The dummy path does not initialize phase configs.
        server_args.cuda_graph_config = CudaGraphConfig(
            decode=PhaseConfig(backend=Backend.FULL, max_bs=512),
            prefill=PhaseConfig(backend=prefill_backend, max_bs=512),
        )
        server_args._resolved_overrides = []
        server_args._cuda_graph_config_locked = (
            {(Phase.PREFILL, "backend")} if lock_prefill_backend else set()
        )
        return server_args
    @override_platform(is_cuda=True, is_hip=False)
    def test_encoder_swa_replay_is_rejected_in_model_hook_order(self):
        """The V4.1 validator runs before the CP validator declares attn_cp_size,
        so encoder SWA replay used to pass resolution with vision prefill CP."""
        args = self._args(
            enable_encoder_swa_bounded_replay=True,
            max_running_requests=4,
            chunked_prefill_size=128,
        )
        with self.assertRaisesRegex(
            ValueError,
            "encoder-swa-bounded-replay does not support context parallelism",
        ):
            handle_model_specific_adjustments(args)
    def test_zigzag_is_rejected_only_with_vision(self):
        with self.assertRaisesRegex(ValueError, "requires --cp-strategy interleave"):
            validate_deepseek_v41_features(self._args(cp_strategy="zigzag"))
        validate_deepseek_v41_features(
            self._args(cp_strategy="zigzag", vision_n_layers=0)
        )
    def test_prefill_graph_explicit_rejects_and_default_resolves_eager(self):
        with self.assertRaisesRegex(ValueError, "runs eager prefill"):
            validate_deepseek_v41_features(
                self._args(prefill_backend=Backend.BREAKABLE, lock_prefill_backend=True)
            )
        args = self._args(prefill_backend=Backend.BREAKABLE)
        validate_deepseek_v41_features(args)
        self.assertEqual(
            resolution_result(args, "cuda_graph_config").prefill.backend,
            Backend.DISABLED,
        )
    def test_dspark_with_decoder_swa_bounded_replay_is_rejected(self):
        with self.assertRaisesRegex(ValueError, "DSpark.*decoder-swa-bounded-replay"):
            validate_deepseek_v41_features(
                self._args(
                    speculative_algorithm="DSPARK",
                    enable_decoder_swa_bounded_replay=True,
                )
            )
 if __name__ == "__main__":
    unittest.main()
Author	SHA1	Message	Date
injet	11e5ba6e8f	update .gitignore build-sglang-image / build (push) Successful in 28m22s Details	2026-09-23 16:42:46 +08:00
injet	fb341f8de5	更新 .gitignore build-sglang-image / build (push) Successful in 32m5s Details	2026-09-23 15:43:38 +08:00