deploy: archive b300 ds41 compose files; skip CI for deploy/ and .gitea/ changes

2026-09-24 11:49:37 +08:00
parent db7d2cb7db
commit 67d8368a84
34 changed files with 1858 additions and 0 deletions
@@ -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