From 735434fcdee8f6b0a7fae74c6f60d8af9e7a7b8d Mon Sep 17 00:00:00 2001 From: "minke.yu" Date: Mon, 28 Sep 2026 16:47:16 +0800 Subject: [PATCH] deploy: k8s RBG 3p1d cw manifest; D cg512 + load-balance-method total_requests --- deploy/b300-ds41/k8s/ds41-3p1d-rbg-cw.yaml | 451 +++++++++++++++++++++ 1 file changed, 451 insertions(+) create mode 100644 deploy/b300-ds41/k8s/ds41-3p1d-rbg-cw.yaml diff --git a/deploy/b300-ds41/k8s/ds41-3p1d-rbg-cw.yaml b/deploy/b300-ds41/k8s/ds41-3p1d-rbg-cw.yaml new file mode 100644 index 000000000..06ddbb6da --- /dev/null +++ b/deploy/b300-ds41/k8s/ds41-3p1d-rbg-cw.yaml @@ -0,0 +1,451 @@ +# ds41-3p1d: DeepSeek-V4.1-Flash 3P1D PD 分离（cs32k + OTLP trace），RBG 版 +# 拓扑: 3×prefill(tp2+ep2+cp2, cs32k, dspark, hicache L3) + 1×decode(tp2+ep2+dp2, cg512, dspark, +# load-balance-method=total_requests 按请求数分流) + mooncake-master(hicache L3 store) + router(mini-lb PD) +# 全部钉 b300-01（单机 8 卡，hostNetwork + hostPID——mooncake NVLink-intra 跨 Pod CUDA IPC 必需， +# 等同 docker compose 的 pid: host；参考 AGENTS.md「部署四要素」） +# 镜像已侧载 containerd: docker.io/ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix（IfNotPresent） +# 参数来源: deploy/b300-ds41/dockerserve-3p1d-otlp-cs32k.yml（docker compose 版） +# 对外: 仅 ClusterIP Service ds41-3p1d:50002（router 用普通 Pod 网络，不占宿主机端口， +# 天然不对宿主机/外网暴露）；new-api-gw 用集群 DNS http://ds41-3p1d:50002/v1 访问 +# trace: OTLP → 127.0.0.1:4317（同节点 jaeger-trace cw，badger 6h 轮窗） +apiVersion: workloads.x-k8s.io/v1alpha2 +kind: RoleBasedGroup +metadata: + name: ds41-3p1d + labels: + app: ds41-3p1d + sglang-model: ds-v41-flash +spec: + roleTemplates: + - name: prefill-base + template: + metadata: + labels: + sglang-model: ds-v41-flash + sglang-role: prefill + spec: + hostNetwork: true + hostPID: true + dnsPolicy: ClusterFirstWithHostNet + nodeSelector: + kubernetes.io/hostname: b300-01 + containers: + - name: sglang + image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix + imagePullPolicy: IfNotPresent + command: + - /bin/bash + - -c + - | + exec sglang serve \ + --trust-remote-code \ + --model-path /data/models/DeepSeek-V4.1-Flash \ + --tp 2 --ep-size 2 \ + --enable-prefill-cp --cp-strategy interleave \ + --chunked-prefill-size 32768 --max-prefill-tokens 32768 \ + --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 256 \ + --tokenizer-worker-num 8 \ + --host 0.0.0.0 --port "$SGLANG_PORT" \ + --enable-cache-report --enable-metrics \ + --speculative-algorithm DSPARK --speculative-dspark-block-size 5 \ + --enable-hierarchical-cache \ + --hicache-ratio 2 \ + --hicache-mem-layout page_first_direct \ + --hicache-io-backend direct \ + --hicache-write-policy write_through \ + --hicache-storage-backend mooncake \ + --hicache-storage-prefetch-policy wait_complete \ + --hicache-size 0 \ + --disaggregation-mode prefill \ + --disaggregation-transfer-backend mooncake \ + --disaggregation-bootstrap-port "$SGLANG_BOOTSTRAP_PORT" \ + --enable-trace \ + --trace-modules request,mooncake \ + --otlp-traces-endpoint 127.0.0.1:4317 \ + --otlp-service-name "$OTLP_NAME" + env: + - name: SGLANG_TORCH_PROFILER_DIR + value: /data/ymk/prof/torch + - name: SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE + value: "1" + - name: SGLANG_RAGGED_VERIFY_MODE + value: static + - name: MC_INTRANODE_NVLINK + value: "true" + - name: MC_INTRA_NVLINK + value: "true" + - name: SGLANG_MOONCAKE_SEND_AUX_TCP + value: "1" + - name: SGLANG_HICACHE_MOONCAKE_CONFIG_PATH + value: /data/ymk/ds41/mooncake-store.json + - name: SGLANG_DISAGGREGATION_QUEUE_SIZE + value: "16" + - name: SGLANG_DISAGGREGATION_THREAD_POOL_SIZE + value: "32" + - name: TZ + value: Asia/Shanghai + readinessProbe: + httpGet: + path: /health + port: metrics + initialDelaySeconds: 60 + periodSeconds: 10 + timeoutSeconds: 5 + failureThreshold: 90 + resources: + requests: + cpu: "32" + memory: 220Gi + nvidia.com/gpu: "2" + limits: + cpu: "96" + memory: 950Gi + nvidia.com/gpu: "2" + securityContext: + privileged: true + volumeMounts: + - name: data + mountPath: /data + - name: sglang-cache + mountPath: /root/.cache/sglang + - name: dshm + mountPath: /dev/shm + volumes: + - name: data + hostPath: + path: /data + type: Directory + - name: sglang-cache + hostPath: + path: /data/ymk/cache/sglang + type: Directory + - name: dshm + emptyDir: + medium: Memory + sizeLimit: 32Gi + - name: decode-base + template: + metadata: + labels: + sglang-model: ds-v41-flash + sglang-role: decode + spec: + hostNetwork: true + hostPID: true + dnsPolicy: ClusterFirstWithHostNet + nodeSelector: + kubernetes.io/hostname: b300-01 + containers: + - name: sglang + image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix + imagePullPolicy: IfNotPresent + command: + - /bin/bash + - -c + - | + exec 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 512 \ + --load-balance-method total_requests \ + --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 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 \ + --enable-trace \ + --trace-modules request,mooncake \ + --otlp-traces-endpoint 127.0.0.1:4317 \ + --otlp-service-name ds41-3p1d-d1 + env: + - name: SGLANG_TORCH_PROFILER_DIR + value: /data/ymk/prof/torch + - name: SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE + value: "1" + - name: SGLANG_RAGGED_VERIFY_MODE + value: static + - name: MC_INTRANODE_NVLINK + value: "true" + - name: MC_INTRA_NVLINK + value: "true" + - name: SGLANG_MOONCAKE_SEND_AUX_TCP + value: "1" + - name: SGLANG_DISAGGREGATION_QUEUE_SIZE + value: "16" + - name: SGLANG_DISAGGREGATION_THREAD_POOL_SIZE + value: "32" + - name: TZ + value: Asia/Shanghai + ports: + - name: metrics + containerPort: 30001 + readinessProbe: + httpGet: + path: /health + port: metrics + initialDelaySeconds: 60 + periodSeconds: 10 + timeoutSeconds: 5 + failureThreshold: 90 + resources: + requests: + cpu: "32" + memory: 100Gi + nvidia.com/gpu: "2" + limits: + cpu: "96" + memory: 600Gi + nvidia.com/gpu: "2" + securityContext: + privileged: true + volumeMounts: + - name: data + mountPath: /data + - name: sglang-cache + mountPath: /root/.cache/sglang + - name: dshm + mountPath: /dev/shm + volumes: + - name: data + hostPath: + path: /data + type: Directory + - name: sglang-cache + hostPath: + path: /data/ymk/cache/sglang + type: Directory + - name: dshm + emptyDir: + medium: Memory + sizeLimit: 32Gi + roles: + - name: mooncake-master + replicas: 1 + standalonePattern: + template: + metadata: + labels: + app: ds41-3p1d-mooncake-master + spec: + hostNetwork: true + dnsPolicy: ClusterFirstWithHostNet + nodeSelector: + kubernetes.io/hostname: b300-01 + containers: + - name: mooncake-master + image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix + imagePullPolicy: IfNotPresent + command: + - /bin/bash + - -c + - | + exec /opt/sglang/bin/mooncake_master \ + --port 50051 \ + --enable_http_metadata_server=true \ + --http_metadata_server_port=18080 \ + --eviction_high_watermark_ratio=0.90 + readinessProbe: + tcpSocket: + port: 50051 + initialDelaySeconds: 5 + periodSeconds: 5 + failureThreshold: 60 + resources: + requests: + cpu: "1" + memory: 8Gi + limits: + cpu: "4" + memory: 64Gi + - name: p1 + replicas: 1 + dependencies: + - mooncake-master + standalonePattern: + templateRef: + name: prefill-base + patch: + metadata: + labels: + app: ds41-3p1d-p1 + spec: + containers: + - name: sglang + env: + - name: CUDA_VISIBLE_DEVICES + value: "0,1" + - name: SGLANG_PORT + value: "30000" + - name: SGLANG_BOOTSTRAP_PORT + value: "8998" + - name: OTLP_NAME + value: ds41-3p1d-p1 + ports: + - name: metrics + containerPort: 30000 + - name: p2 + replicas: 1 + dependencies: + - mooncake-master + standalonePattern: + templateRef: + name: prefill-base + patch: + metadata: + labels: + app: ds41-3p1d-p2 + spec: + containers: + - name: sglang + env: + - name: CUDA_VISIBLE_DEVICES + value: "2,3" + - name: SGLANG_PORT + value: "30010" + - name: SGLANG_BOOTSTRAP_PORT + value: "8999" + - name: OTLP_NAME + value: ds41-3p1d-p2 + ports: + - name: metrics + containerPort: 30010 + - name: p3 + replicas: 1 + dependencies: + - mooncake-master + standalonePattern: + templateRef: + name: prefill-base + patch: + metadata: + labels: + app: ds41-3p1d-p3 + spec: + containers: + - name: sglang + env: + - name: CUDA_VISIBLE_DEVICES + value: "4,5" + - name: SGLANG_PORT + value: "30020" + - name: SGLANG_BOOTSTRAP_PORT + value: "9000" + - name: OTLP_NAME + value: ds41-3p1d-p3 + ports: + - name: metrics + containerPort: 30020 + - name: d1 + replicas: 1 + dependencies: + - mooncake-master + standalonePattern: + templateRef: + name: decode-base + patch: + metadata: + labels: + app: ds41-3p1d-d1 + spec: + containers: + - name: sglang + env: + - name: CUDA_VISIBLE_DEVICES + value: "6,7" + - name: router + replicas: 1 + dependencies: + - p1 + - p2 + - p3 + - d1 + standalonePattern: + template: + metadata: + labels: + app: ds41-3p1d-router + spec: + # 入口不走 hostNetwork：普通 Pod 网络 + ClusterIP，天然不对宿主机/外网暴露。 + # P/D 地址用节点内网 IP（hostNetwork 监听在 192.168.1.243 上，Calico 可达）。 + nodeSelector: + kubernetes.io/hostname: b300-01 + containers: + - name: router + image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix + imagePullPolicy: IfNotPresent + command: + - /bin/bash + - -c + - | + exec sglang-router launch \ + --mini-lb --pd-disaggregation \ + --host 0.0.0.0 --port 50002 \ + --prefill http://192.168.1.243:30000 8998 \ + --prefill http://192.168.1.243:30010 8999 \ + --prefill http://192.168.1.243:30020 9000 \ + --decode http://192.168.1.243:30001 + ports: + - name: http + containerPort: 50002 + readinessProbe: + httpGet: + path: /health + port: http + initialDelaySeconds: 5 + periodSeconds: 10 + timeoutSeconds: 5 + failureThreshold: 30 + resources: + requests: + cpu: "1" + memory: 4Gi + limits: + cpu: "8" + memory: 16Gi +--- +apiVersion: v1 +kind: Service +metadata: + name: ds41-3p1d + labels: + app: ds41-3p1d +spec: + type: ClusterIP + selector: + rbg.workloads.x-k8s.io/group-name: ds41-3p1d + rbg.workloads.x-k8s.io/role-name: router + ports: + - name: http + port: 50002 + targetPort: 50002 +--- +apiVersion: monitoring.coreos.com/v1 +kind: PodMonitor +metadata: + name: ds41-3p1d + labels: + release: kube-prometheus-stack +spec: + selector: + matchLabels: + sglang-model: ds-v41-flash + podMetricsEndpoints: + - interval: 15s + path: /metrics + port: metrics