diff --git a/deploy/b300-ds41/dockerserve-benchb-1p1d-x2.yml b/deploy/b300-ds41/dockerserve-benchb-1p1d-x2.yml index e475a4d141..02fa3c6ca8 100644 --- a/deploy/b300-ds41/dockerserve-benchb-1p1d-x2.yml +++ b/deploy/b300-ds41/dockerserve-benchb-1p1d-x2.yml @@ -1,229 +1,229 @@ -# 【阶段B 新旧基线 2026-10-18】两套 1P1D PD 并行:旧版 vs 新版同部署对比 -# 旧栈:P=GPU0,1:31000 D=GPU2,3:31200 router=31400 master=50051(镜像 ∈ tag 26.10.18) -# 新栈:P=GPU4,5:31100 D=GPU6,7:31300 router=31500 master=50061(g9i-est-td-e4391748e) -# 配置 = 线上 k8s P/D spec 原样(mem 0.85、ratio 1.0、write_through、wait_complete、 -# dspark b5、cp2-P / dp2-D),仅改端口/bootstrap/master;OTLP trace 不陪跑。 -# NVLink-intra 传输四件套(pid:host + CUSTOM_MEM_POOL + MC_INTRA 双拼写 + AUX_TCP)按 AGENTS.md 铁律。 -# 两套各挂各的 mooncake master(rank 名在同 master 下必须唯一,混挂会撞 localhost-d0tXpYcZ)。 -# 新栈复用阶段A已暖的 cache /data/ymk/cache/sglang-e43917(flashinfer 0.7.2 autotune 已跑过)。 -# ⚠️ 用前必须 down 阶段A(docker compose -p bencha down)。 -# 用法:docker compose -p benchb -f dockerserve-benchb-1p1d-x2.yml up -d -# 入口:旧栈 http://127.0.0.1:31400 新栈 http://127.0.0.1:31500(api-key deepseek-v4-flash-0731-key) - -x-common: &common - shm_size: "32gb" - ipc: host - pid: host - privileged: true - network_mode: host - deploy: - resources: - reservations: - devices: - - driver: nvidia - count: all - capabilities: [gpu] - -x-pd-env: &pd-env - SGLANG_TORCH_PROFILER_DIR: /data/ymk/prof/torch - SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE: "1" - SGLANG_RAGGED_VERIFY_MODE: static - SGLANG_MOONCAKE_CUSTOM_MEM_POOL: INTRA_NODE_NVLINK - 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" - -x-p-extra-hosts: &p-extra-hosts - # mooncake rank 后缀主机名(84fc632088 要求可解析) - - "localhost-d0t0p0c0:127.0.0.1" - - "localhost-d0t1p0c1:127.0.0.1" - -services: - # ---------- 旧栈(tag 26.10.18) ---------- - master-old: - image: ymkymx/sglang:dsv41-pd-visioncp-baba18bc7d-local-20261010-2310 - container_name: benchb-master-old - network_mode: host - command: > - /opt/sglang/bin/mooncake_master --port 50051 - --enable_http_metadata_server=true --http_metadata_server_port=8080 - --eviction_high_watermark_ratio=0.90 - - p-old: - <<: *common - image: ymkymx/sglang:dsv41-pd-visioncp-baba18bc7d-local-20261010-2310 - container_name: benchb-p-old - extra_hosts: *p-extra-hosts - volumes: - - /data:/data - - /data/ymk/cache/sglang:/root/.cache/sglang - environment: - <<: *pd-env - SGLANG_HICACHE_MOONCAKE_CONFIG_PATH: /data/ymk/ds41/mooncake-store-tcp.json - SGLANG_HICACHE_PREFETCH_IO_THREADS: "4" - 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 0.85 - --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 256 - --tokenizer-worker-num 8 - --host 0.0.0.0 --port 31000 - --enable-cache-report --enable-metrics - --speculative-algorithm DSPARK --speculative-dspark-block-size 5 - --enable-hierarchical-cache - --hicache-ratio 1.0 - --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 9100 - - d-old: - <<: *common - image: ymkymx/sglang:dsv41-pd-visioncp-6612af9e0-local-20261011-0740 - container_name: benchb-d-old - volumes: - - /data:/data - - /data/ymk/cache/sglang:/root/.cache/sglang - environment: - <<: *pd-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 - --dp-size 2 --enable-dp-attention --enable-dp-lm-head - --mem-fraction-static 0.85 - --attention-backend dsv4 - --moe-runner-backend flashinfer_mxfp4 - --cuda-graph-max-bs-decode 160 - --max-running-requests 300 - --tokenizer-worker-num 8 - --host 0.0.0.0 --port 31200 - --enable-cache-report --enable-metrics - --speculative-algorithm DSPARK --speculative-dspark-block-size 5 - --disaggregation-mode decode - --disaggregation-transfer-backend mooncake - --disaggregation-bootstrap-port 9101 - - router-old: - image: ymkymx/sglang:dsv41-pd-visioncp-baba18bc7d-local-20261010-2310 - container_name: benchb-router-old - network_mode: host - entrypoint: sglang-router - command: > - launch --mini-lb --pd-disaggregation - --prefill http://127.0.0.1:31000 9100 - --decode http://127.0.0.1:31200 - --host 0.0.0.0 --port 31400 - --api-key deepseek-v4-flash-0731-key - - # ---------- 新栈(g9i-est-td @ e4391748e) ---------- - master-new: - image: ymkymx/sglang:g9i-est-td-1d2610bbc-local-20261018-1506 - container_name: benchb-master-new - network_mode: host - command: > - /opt/sglang/bin/mooncake_master --port 50061 - --enable_http_metadata_server=true --http_metadata_server_port=8081 - --eviction_high_watermark_ratio=0.90 - - p-new: - <<: *common - image: ymkymx/sglang:g9i-est-td-1d2610bbc-local-20261018-1506 - container_name: benchb-p-new - extra_hosts: *p-extra-hosts - volumes: - - /data:/data - - /data/ymk/cache/sglang-e43917:/root/.cache/sglang - environment: - <<: *pd-env - SGLANG_HICACHE_MOONCAKE_CONFIG_PATH: /data/ymk/ds41/mooncake-store-tcp-50061.json - SGLANG_HICACHE_PREFETCH_IO_THREADS: "4" - 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 0.85 - --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 256 - --tokenizer-worker-num 8 - --host 0.0.0.0 --port 31100 - --enable-cache-report --enable-metrics - --speculative-algorithm DSPARK --speculative-dspark-block-size 5 - --enable-hierarchical-cache - --hicache-ratio 1.0 - --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 9110 - - d-new: - <<: *common - image: ymkymx/sglang:g9i-est-td-1d2610bbc-local-20261018-1506 - container_name: benchb-d-new - volumes: - - /data:/data - - /data/ymk/cache/sglang-e43917:/root/.cache/sglang - environment: - <<: *pd-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 0.85 - --attention-backend dsv4 - --moe-runner-backend flashinfer_mxfp4 - --cuda-graph-max-bs-decode 160 - --max-running-requests 300 - --tokenizer-worker-num 8 - --host 0.0.0.0 --port 31300 - --enable-cache-report --enable-metrics - --skip-server-warmup - --speculative-algorithm DSPARK --speculative-dspark-block-size 5 - --disaggregation-mode decode - --disaggregation-transfer-backend mooncake - --disaggregation-bootstrap-port 9111 - - router-new: - image: ymkymx/sglang:g9i-est-td-1d2610bbc-local-20261018-1506 - container_name: benchb-router-new - network_mode: host - entrypoint: sglang-router - command: > - launch --mini-lb --pd-disaggregation - --prefill http://127.0.0.1:31100 9110 - --decode http://127.0.0.1:31300 - --host 0.0.0.0 --port 31500 - --api-key deepseek-v4-flash-0731-key +# 【阶段B 新旧基线 2026-10-18】两套 1P1D PD 并行:旧版 vs 新版同部署对比 +# 旧栈:P=GPU0,1:32100 D=GPU2,3:32200 router=32300 master=50051(镜像 ∈ tag 26.10.18) +# 新栈:P=GPU4,5:32400 D=GPU6,7:32500 router=32600 master=50061(g9i-est-td-e4391748e) +# 配置 = 线上 k8s P/D spec 原样(mem 0.85、ratio 1.0、write_through、wait_complete、 +# dspark b5、cp2-P / dp2-D),仅改端口/bootstrap/master;OTLP trace 不陪跑。 +# NVLink-intra:pid:host + MC_INTRA 双拼写 + AUX_TCP(与线上 k8s spec 逐字对齐;CUSTOM_MEM_POOL 实测触发段错误,不设)。 +# 两套各挂各的 mooncake master(rank 名在同 master 下必须唯一,混挂会撞 localhost-d0tXpYcZ)。 +# 新栈复用阶段A已暖的 cache /data/ymk/cache/sglang-e43917(flashinfer 0.7.2 autotune 已跑过)。 +# ⚠️ 用前必须 down 阶段A(docker compose -p bencha down)。 +# 用法:docker compose -p benchb -f dockerserve-benchb-1p1d-x2.yml up -d +# 入口:旧栈 http://127.0.0.1:32300 新栈 http://127.0.0.1:32600(api-key deepseek-v4-flash-0731-key) + +x-common: &common + shm_size: "32gb" + ipc: host + pid: host + privileged: true + network_mode: host + deploy: + resources: + reservations: + devices: + - driver: nvidia + count: all + capabilities: [gpu] + +x-pd-env: &pd-env + SGLANG_TORCH_PROFILER_DIR: /data/ymk/prof/torch + 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" + +x-p-extra-hosts: &p-extra-hosts + # mooncake rank 后缀主机名(84fc632088 要求可解析) + - "localhost-d0t0p0c0:127.0.0.1" + - "localhost-d0t1p0c1:127.0.0.1" + +services: + # ---------- 旧栈(tag 26.10.18) ---------- + master-old: + image: ymkymx/sglang:dsv41-pd-visioncp-baba18bc7d-local-20261010-2310 + container_name: benchb-master-old + network_mode: host + command: > + /opt/sglang/bin/mooncake_master --port 50051 + --enable_http_metadata_server=true --http_metadata_server_port=8080 + --eviction_high_watermark_ratio=0.90 + + p-old: + <<: *common + image: ymkymx/sglang:dsv41-pd-visioncp-baba18bc7d-local-20261010-2310 + container_name: benchb-p-old + extra_hosts: *p-extra-hosts + volumes: + - /data:/data + - /data/ymk/cache/sglang:/root/.cache/sglang + environment: + <<: *pd-env + SGLANG_HICACHE_MOONCAKE_CONFIG_PATH: /data/ymk/ds41/mooncake-store-tcp.json + SGLANG_HICACHE_PREFETCH_IO_THREADS: "4" + 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 0.85 + --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 256 + --tokenizer-worker-num 8 + --host 0.0.0.0 --port 32100 + --enable-cache-report --enable-metrics + --speculative-algorithm DSPARK --speculative-dspark-block-size 5 + --enable-hierarchical-cache + --hicache-ratio 1.0 + --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 9601 + + d-old: + <<: *common + image: ymkymx/sglang:dsv41-pd-visioncp-6612af9e0-local-20261011-0740 + container_name: benchb-d-old + volumes: + - /data:/data + - /data/ymk/cache/sglang:/root/.cache/sglang + environment: + <<: *pd-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 + --dp-size 2 --enable-dp-attention --enable-dp-lm-head + --mem-fraction-static 0.85 + --attention-backend dsv4 + --moe-runner-backend flashinfer_mxfp4 + --cuda-graph-max-bs-decode 160 + --max-running-requests 300 + --tokenizer-worker-num 8 + --host 0.0.0.0 --port 32200 + --enable-cache-report --enable-metrics + --speculative-algorithm DSPARK --speculative-dspark-block-size 5 + --disaggregation-mode decode + --disaggregation-transfer-backend mooncake + --disaggregation-bootstrap-port 9602 + + router-old: + image: ymkymx/sglang:dsv41-pd-visioncp-baba18bc7d-local-20261010-2310 + container_name: benchb-router-old + network_mode: host + entrypoint: sglang-router + command: > + launch --mini-lb --pd-disaggregation + --prefill http://127.0.0.1:32100 9601 + --decode http://127.0.0.1:32200 + --host 0.0.0.0 --port 32300 + --api-key deepseek-v4-flash-0731-key + + # ---------- 新栈(g9i-est-td @ e4391748e) ---------- + master-new: + image: ymkymx/sglang:g9i-est-td-148936bcb-local-20261018-1803 + container_name: benchb-master-new + network_mode: host + command: > + /opt/sglang/bin/mooncake_master --port 50061 + --enable_http_metadata_server=true --http_metadata_server_port=8081 + --metrics_port 9004 + --eviction_high_watermark_ratio=0.90 + + p-new: + <<: *common + image: ymkymx/sglang:g9i-est-td-148936bcb-local-20261018-1803 + container_name: benchb-p-new + extra_hosts: *p-extra-hosts + volumes: + - /data:/data + - /data/ymk/cache/sglang-e43917:/root/.cache/sglang + environment: + <<: *pd-env + SGLANG_HICACHE_MOONCAKE_CONFIG_PATH: /data/ymk/ds41/mooncake-store-tcp-50061.json + SGLANG_HICACHE_PREFETCH_IO_THREADS: "4" + 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 0.85 + --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 256 + --tokenizer-worker-num 8 + --host 0.0.0.0 --port 32400 + --enable-cache-report --enable-metrics + --speculative-algorithm DSPARK --speculative-dspark-block-size 5 + --enable-hierarchical-cache + --hicache-ratio 1.0 + --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 9611 + + d-new: + <<: *common + image: ymkymx/sglang:g9i-est-td-148936bcb-local-20261018-1803 + container_name: benchb-d-new + volumes: + - /data:/data + - /data/ymk/cache/sglang-e43917:/root/.cache/sglang + environment: + <<: *pd-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 0.85 + --attention-backend dsv4 + --moe-runner-backend flashinfer_mxfp4 + --cuda-graph-max-bs-decode 160 + --max-running-requests 300 + --tokenizer-worker-num 8 + --host 0.0.0.0 --port 32500 + --enable-cache-report --enable-metrics + --skip-server-warmup + --speculative-algorithm DSPARK --speculative-dspark-block-size 5 + --disaggregation-mode decode + --disaggregation-transfer-backend mooncake + --disaggregation-bootstrap-port 9612 + + router-new: + image: ymkymx/sglang:g9i-est-td-148936bcb-local-20261018-1803 + container_name: benchb-router-new + network_mode: host + entrypoint: sglang-router + command: > + launch --mini-lb --pd-disaggregation + --prefill http://127.0.0.1:32400 9611 + --decode http://127.0.0.1:32500 + --host 0.0.0.0 --port 32600 + --api-key deepseek-v4-flash-0731-key