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 +1,67 @@
+# 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