deploy: archive b300 ds41 compose files; skip CI for deploy/ and .gitea/ changes
This commit is contained in:
@@ -13,6 +13,11 @@ name: build-sglang-image
|
||||
on:
|
||||
push:
|
||||
branches: [dsv41-pd, dsv41-pd-visioncp]
|
||||
# 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）
|
||||
|
||||
@@ -0,0 +1,33 @@
|
||||
# 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
|
||||
@@ -0,0 +1,171 @@
|
||||
# 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
|
||||
@@ -0,0 +1,43 @@
|
||||
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}'
|
||||
@@ -0,0 +1,43 @@
|
||||
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}'
|
||||
@@ -0,0 +1,42 @@
|
||||
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}'
|
||||
@@ -0,0 +1,160 @@
|
||||
# 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
|
||||
@@ -0,0 +1,44 @@
|
||||
# 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
|
||||
@@ -0,0 +1,50 @@
|
||||
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}'
|
||||
@@ -0,0 +1,51 @@
|
||||
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}'
|
||||
@@ -0,0 +1,50 @@
|
||||
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}'
|
||||
@@ -0,0 +1,51 @@
|
||||
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}'
|
||||
@@ -0,0 +1,44 @@
|
||||
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}'
|
||||
@@ -0,0 +1,44 @@
|
||||
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}'
|
||||
@@ -0,0 +1,44 @@
|
||||
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}'
|
||||
@@ -0,0 +1,62 @@
|
||||
# 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
|
||||
@@ -0,0 +1,42 @@
|
||||
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}'
|
||||
@@ -0,0 +1,44 @@
|
||||
# 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
|
||||
@@ -0,0 +1,47 @@
|
||||
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}'
|
||||
@@ -0,0 +1,51 @@
|
||||
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
|
||||
@@ -0,0 +1,50 @@
|
||||
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}'
|
||||
@@ -0,0 +1,55 @@
|
||||
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}'
|
||||
@@ -0,0 +1,53 @@
|
||||
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
|
||||
@@ -0,0 +1,52 @@
|
||||
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}'
|
||||
@@ -0,0 +1,57 @@
|
||||
# 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
|
||||
@@ -0,0 +1,54 @@
|
||||
# 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
|
||||
@@ -0,0 +1,67 @@
|
||||
# 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
|
||||
@@ -0,0 +1,65 @@
|
||||
# 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
|
||||
@@ -0,0 +1,59 @@
|
||||
# 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
|
||||
@@ -0,0 +1,42 @@
|
||||
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}'
|
||||
@@ -0,0 +1,42 @@
|
||||
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}'
|
||||
@@ -0,0 +1,92 @@
|
||||
# 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
|
||||
@@ -0,0 +1,43 @@
|
||||
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}'
|
||||
|
||||
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"master_server_address": "127.0.0.1:50051",
|
||||
"metadata_server": "P2PHANDSHAKE",
|
||||
"global_segment_size": "300gb",
|
||||
"protocol": "tcp"
|
||||
}
|
||||
Reference in New Issue
Block a user