# 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