deploy(g9i): merged ns+td gateway, 32-request P queue cap (p95 5.70s)

This commit is contained in:
2026-11-15 22:25:33 +08:00
parent b3d6d19c7d
commit b8b205b367
@@ -0,0 +1,544 @@
apiVersion: workloads.x-k8s.io/v1alpha2
kind: RoleBasedGroup
metadata:
annotations:
rbg.workloads.x-k8s.io/discovery-config-mode: refine
labels:
app: ds41-gist-exp
kongming.io/managed-by: kongming
kongming.io/node-group-id: ng-damg6d4grhalvvbgbbrg
kongming.io/project-id: prj-d7te67bj0sq2fgdrmbig
kongming.io/resource-type: custom-workload
sglang-model: ds-v41-flash
name: ds41-gist-exp
namespace: prj-d7te67bj0sq2fgdrmbig
spec:
roles:
- minReadySeconds: 0
name: mooncake-master
podManagementPolicy: Parallel
replicas: 1
standalonePattern:
template:
metadata:
annotations:
prometheus.io/path: /metrics
prometheus.io/port: '19003'
prometheus.io/scheme: http
labels:
app: ds41-l3ssd-mooncake
kongming.io/managed-by: kongming
kongming.io/node-group-id: ng-damg6d4grhalvvbgbbrg
kongming.io/project-id: prj-d7te67bj0sq2fgdrmbig
kongming.io/resource-type: custom-workload
spec:
containers:
- command:
- /bin/bash
- -c
- "# 18081: 宿主机 18080 被 AgentX fake upstream(./fakeup)长期占用;\n# 我们的 P/D\
\ 用 metadata_server=P2PHANDSHAKE,此 HTTP 端口只是 master 可选项。\nexec /opt/sglang/bin/mooncake_master\
\ \\\n --port 50051 --enable_http_metadata_server=true \\\n --http_metadata_server_port=18081\
\ --metrics_port=19003 --eviction_high_watermark_ratio=0.90 --enable_offload=true\
\ --offload_on_evict=false --promotion_on_hit=false --offload_force_evict=false\n"
image: sealos.hub:5000/prj-d7te67bj0sq2fgdrmbig/sglang:recipe-ns-l3ssd-433257c7b-baked-20261115
imagePullPolicy: IfNotPresent
name: mooncake-master
ports:
- containerPort: 19003
name: metrics
protocol: TCP
readinessProbe:
failureThreshold: 60
initialDelaySeconds: 5
periodSeconds: 5
tcpSocket:
port: 50051
resources:
limits:
cpu: '4'
memory: 64Gi
requests:
cpu: '1'
memory: 8Gi
env:
- name: TMPDIR
value: /data/ymk/l3ssd/master-tmp
- name: XDG_CACHE_HOME
value: /data/ymk/l3ssd/master-xdg
dnsPolicy: ClusterFirstWithHostNet
hostNetwork: true
nodeSelector:
kongming.io/node-group-id: ng-damg6d4grhalvvbgbbrg
kongming.io/project-id: prj-d7te67bj0sq2fgdrmbig
kubernetes.io/hostname: b300-01
- dependencies:
- mooncake-master
minReadySeconds: 0
name: p
podManagementPolicy: Parallel
replicas: 1
standalonePattern:
template:
metadata:
annotations:
prometheus.io/path: /metrics
prometheus.io/port: '30000'
prometheus.io/scheme: http
labels:
app: ds41-l3ssd-p
kongming.io/managed-by: kongming
kongming.io/node-group-id: ng-damg6d4grhalvvbgbbrg
kongming.io/project-id: prj-d7te67bj0sq2fgdrmbig
kongming.io/resource-type: custom-workload
spec:
containers:
- command:
- /bin/bash
- -c
- "exec sglang serve \\\n --trust-remote-code --tokenizer-backend fastokens\
\ --model-path /data/models/DeepSeek-V4.1-Flash-1017 --served-model-name\
\ /data/models/DeepSeek-V4.1-Flash \\\n --reasoning-parser auto --tool-call-parser\
\ auto \\\n --default-chat-template-kwargs '{\"thinking\": true, \"\
reasoning_effort\": \"high\"}' \\\n --tp 4 --dp-size 4 --ep-size 4\
\ --enable-dp-attention --enable-dp-lm-head \\\n --moe-a2a-backend\
\ megamoe --dsv4-attn-backend flashmla_mega \\\n --ep-num-redundant-experts\
\ 32 --ep-dispatch-algorithm dynamic \\\n --init-expert-location /data/ymk/gist-dsv41/placement_r32_ep4.json\
\ \\\n --mem-fraction-static 0.80 \\\n --chunked-prefill-size 131072\
\ --max-prefill-tokens 131072 \\\n --max-running-requests 512 --tokenizer-worker-num\
\ 16 \\\n --load-balance-method total_tokens \\\n --speculative-algorithm\
\ DSPARK --speculative-dspark-block-size 3 \\\n --enable-decoder-swa-bounded-replay\
\ --swa-full-tokens-ratio 0.12 \\\n --cuda-graph-max-bs-decode 1 --disable-decode-cuda-graph\
\ \\\n --cuda-graph-backend-prefill breakable \\\n --cuda-graph-bs-prefill\
\ 1024 2048 4096 8192 16384 32768 \\\n --cuda-graph-prefill-max-context\
\ 262144 --cuda-graph-max-seq-len-prefill 262144 \\\n --enable-hierarchical-cache\
\ --hicache-ratio 4 \\\n --hicache-mem-layout page_first_direct --hicache-io-backend\
\ direct \\\n --hicache-write-policy write_through --hicache-storage-backend\
\ mooncake \\\n --hicache-storage-prefetch-policy wait_complete \\\n\
\ --disaggregation-mode prefill --disaggregation-transfer-backend mooncake\
\ \\\n --disaggregation-bootstrap-port 8998 \\\n --expert-balancedness-report-mode\
\ prometheus \\\n --expert-distribution-recorder-buffer-size 64 \\\n\
\ --host 0.0.0.0 --port 30000 --enable-metrics --enable-cache-report\
\ \\\n --enable-trace --trace-modules request,mooncake \\\n --otlp-traces-endpoint\
\ 127.0.0.1:4317 --otlp-service-name gist-exp-p \\\n --watchdog-timeout\
\ 3600 --enable-dp-attention-local-control-broadcast\n"
env:
- name: CUDA_VISIBLE_DEVICES
value: 0,1,2,3
- name: SGLANG_LOG_MS
value: '1'
- name: SGLANG_OPT_DSV41_ENGRAM_PEER_SHARDS
value: '1'
- name: SGLANG_OPT_DSV41_MEGA_MHC_PREFILL
value: '1'
- name: SGLANG_OPT_DSV41_BF16_INDEX_LOGITS
value: '1'
- name: SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK
value: '65536'
- name: SGLANG_DSV4_KV_LAYOUT
value: v41_new
- name: SGLANG_DP_USE_GATHERV
value: '1'
- name: SGLANG_RAGGED_VERIFY_MODE
value: static
- name: SGLANG_ENABLE_DP_SPEC_PREFILL_COORDINATION
value: '0'
- name: SGLANG_NUMA_BIND_V2
value: '0'
- name: SGLANG_DEFAULT_THINKING
value: '1'
- name: SGLANG_DSV41_REASONING_EFFORT
value: high
- name: SGLANG_TIMEOUT_KEEP_ALIVE
value: '900'
- name: SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE
value: '1'
- name: MC_INTRANODE_NVLINK
value: 'true'
- name: MC_INTRA_NVLINK
value: 'true'
- name: SGLANG_MOONCAKE_SEND_AUX_TCP
value: 'true'
- name: SGLANG_HICACHE_MOONCAKE_CONFIG_PATH
value: /data/ymk/ds41/mooncake-store-l3ssd.json
- name: SGLANG_HICACHE_PREFETCH_IO_THREADS
value: '4'
- name: SGLANG_HICACHE_BACKUP_IO_THREADS
value: '4'
- name: SGLANG_HICACHE_TIMING
value: '1'
- name: SGLANG_BATCH_TELEMETRY
value: '1'
- name: SGLANG_ENABLE_METRICS_DP_ATTENTION
value: '1'
- name: SGLANG_ENABLE_METRICS_DEVICE_TIMER
value: '1'
- name: SGLANG_EPLB_HEATMAP_COLLECTION_INTERVAL
value: '100'
- name: SGLANG_MM_TRACE
value: '1'
- name: SGLANG_BATCH_SPAN_MIN_MS
value: '200'
- name: SGLANG_BATCH_SPAN_SAMPLE
value: '0.05'
- name: SGLANG_BATCH_SPAN_MAX_LINKS
value: '8'
- name: SGLANG_BATCH_STAGE_TIMING
value: '1'
- name: SGLANG_BATCH_PASS_SPAN
value: '1'
- name: SGLANG_BATCH_PASS_SPAN_SAMPLE
value: '1.0'
- name: SGLANG_RECV_SPAN
value: '1'
- name: SGLANG_RECV_SPAN_SAMPLE
value: '1.0'
- name: SGLANG_MM_TRACE_SYNC
value: '0'
- name: SGLANG_DISAGGREGATION_FORCE_QUERY_PREFILL_DP_RANK
value: '1'
- name: SGLANG_DISAGGREGATION_WAITING_TIMEOUT
value: '600'
- name: SGLANG_DISAGGREGATION_QUEUE_SIZE
value: '16'
- name: SGLANG_DISAGGREGATION_THREAD_POOL_SIZE
value: '32'
- name: TZ
value: Asia/Shanghai
- name: SGLANG_TRACE_LOOP_SPAN
value: '1'
- name: SGLANG_TRACE_LOOP_SAMPLE
value: '1.0'
- name: SGLANG_FWD_TIMELINE
value: '0'
- name: SGLANG_TRACE_LOOP_DETAIL
value: '1'
- name: SGLANG_TRACE_MOONCAKE_DETAIL
value: '0'
- name: SGLANG_TRACE_BACKUP_DETAIL
value: '1'
- name: SGLANG_ASYNC_BACKUP_SUBMIT
value: '1'
- name: SGLANG_NCCL_ALL_GATHER_IN_OVERLAP_SCHEDULER_SYNC_BATCH
value: '1'
- name: OTEL_SPAN_ATTRIBUTE_COUNT_LIMIT
value: '1024'
- name: SGLANG_MOONCAKE_CLIENT_METRICS_PORT_BASE
value: '9400'
- name: MOONCAKE_OFFLOAD_STORAGE_BACKEND_DESCRIPTOR
value: bucket_storage_backend
- name: MOONCAKE_OFFLOAD_BUCKET_MAX_TOTAL_SIZE
value: '1099511627776'
- name: MOONCAKE_OFFLOAD_TOTAL_SIZE_LIMIT_BYTES
value: '1099511627776'
- name: MOONCAKE_OFFLOAD_BUCKET_EVICTION_POLICY
value: fifo
- name: TMPDIR
value: /data/ymk/l3ssd/p-tmp
- name: XDG_CACHE_HOME
value: /data/ymk/l3ssd/p-xdg
- name: HF_HOME
value: /data/ymk/l3ssd/p-hf
- name: MOONCAKE_OFFLOAD_FLUSH_PARTIAL_BUCKETS
value: '0'
image: sealos.hub:5000/prj-d7te67bj0sq2fgdrmbig/sglang:recipe-ns-l3ssd-433257c7b-baked-20261115
imagePullPolicy: IfNotPresent
name: sglang
ports:
- containerPort: 30000
name: metrics
protocol: TCP
- containerPort: 8998
name: bootstrap
protocol: TCP
- name: mc-0
containerPort: 9400
protocol: TCP
- name: mc-1
containerPort: 9401
protocol: TCP
- name: mc-2
containerPort: 9402
protocol: TCP
- name: mc-3
containerPort: 9403
protocol: TCP
readinessProbe:
failureThreshold: 120
httpGet:
path: /health
port: metrics
initialDelaySeconds: 60
periodSeconds: 10
timeoutSeconds: 5
resources:
limits:
cpu: '96'
memory: 2Ti
nvidia.com/gpu: '4'
requests:
cpu: '32'
memory: 512Gi
nvidia.com/gpu: '4'
securityContext:
privileged: true
volumeMounts:
- mountPath: /data
name: data
- mountPath: /root/.cache/sglang
name: sglang-cache
- mountPath: /dev/shm
name: dshm
- mountPath: /root/.cargo/bin/cargo
name: fake-cargo
readOnly: true
dnsPolicy: ClusterFirstWithHostNet
hostNetwork: true
hostPID: true
nodeSelector:
kongming.io/node-group-id: ng-damg6d4grhalvvbgbbrg
kongming.io/project-id: prj-d7te67bj0sq2fgdrmbig
kubernetes.io/hostname: b300-01
volumes:
- hostPath:
path: /data
type: Directory
name: data
- hostPath:
path: /data/ymk/cache/sglang
type: Directory
name: sglang-cache
- emptyDir:
medium: Memory
sizeLimit: 64Gi
name: dshm
- hostPath:
path: /data/ymk/ds41/fake-cargo
type: File
name: fake-cargo
- dependencies:
- mooncake-master
minReadySeconds: 0
name: d
podManagementPolicy: Parallel
replicas: 1
standalonePattern:
template:
metadata:
annotations:
prometheus.io/path: /metrics
prometheus.io/port: '30300'
prometheus.io/scheme: http
labels:
app: ds41-l3ssd-d
kongming.io/managed-by: kongming
kongming.io/node-group-id: ng-damg6d4grhalvvbgbbrg
kongming.io/project-id: prj-d7te67bj0sq2fgdrmbig
kongming.io/resource-type: custom-workload
spec:
containers:
- command:
- /bin/bash
- -c
- "exec sglang serve \\\n --trust-remote-code --tokenizer-backend fastokens\
\ --model-path /data/models/DeepSeek-V4.1-Flash-1017 --served-model-name\
\ /data/models/DeepSeek-V4.1-Flash \\\n --reasoning-parser auto --tool-call-parser\
\ auto \\\n --default-chat-template-kwargs '{\"thinking\": true, \"\
reasoning_effort\": \"high\"}' \\\n --tp 4 --dp-size 4 --ep-size 4\
\ --enable-dp-attention --enable-dp-lm-head \\\n --enable-fp32-lm-head\
\ --enable-dp-attention-local-control-broadcast \\\n --moe-a2a-backend\
\ megamoe --dsv4-attn-backend flashmla_mega \\\n --ep-num-redundant-experts\
\ 64 --ep-dispatch-algorithm dynamic \\\n --init-expert-location /data/ymk/gist-dsv41/placement_r64_ep4.json\
\ \\\n --mem-fraction-static 0.80 \\\n --speculative-algorithm DSPARK\
\ --speculative-dspark-block-size 3 \\\n --stream-interval 32 --swa-prefix-tails\
\ 2048 --enable-decoder-swa-bounded-replay \\\n --max-running-requests\
\ 512 --cuda-graph-max-bs-decode 512 \\\n --chunked-prefill-size 32768\
\ --max-prefill-tokens 8192 \\\n --disaggregation-mode decode --disaggregation-transfer-backend\
\ mooncake \\\n --host 0.0.0.0 --port 30300 --enable-metrics --enable-cache-report\
\ \\\n --enable-trace --trace-modules request,mooncake \\\n --otlp-traces-endpoint\
\ 127.0.0.1:4317 --otlp-service-name gist-exp-d \\\n --watchdog-timeout\
\ 3600\n"
env:
- name: CUDA_VISIBLE_DEVICES
value: 4,5,6,7
- name: SGLANG_RAGGED_VERIFY_MODE
value: static
- name: SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE
value: '1'
- name: SGLANG_DSV4_KV_LAYOUT
value: v41_new
- name: SGLANG_DEFAULT_THINKING
value: '1'
- name: SGLANG_DSV41_REASONING_EFFORT
value: high
- name: MC_INTRANODE_NVLINK
value: 'true'
- name: MC_INTRA_NVLINK
value: 'true'
- name: SGLANG_MOONCAKE_SEND_AUX_TCP
value: 'true'
- name: SGLANG_ENABLE_METRICS_DP_ATTENTION
value: '1'
- name: SGLANG_BATCH_TELEMETRY
value: '1'
- name: SGLANG_BATCH_SPAN_SAMPLE
value: '0.1'
- name: SGLANG_DISAGGREGATION_WAITING_TIMEOUT
value: '600'
- name: SGLANG_DISAGGREGATION_QUEUE_SIZE
value: '16'
- name: SGLANG_DISAGGREGATION_THREAD_POOL_SIZE
value: '32'
- name: TZ
value: Asia/Shanghai
- name: OTEL_SPAN_ATTRIBUTE_COUNT_LIMIT
value: '1024'
- name: TMPDIR
value: /data/ymk/l3ssd/d-tmp
- name: XDG_CACHE_HOME
value: /data/ymk/l3ssd/d-xdg
- name: HF_HOME
value: /data/ymk/l3ssd/d-hf
image: sealos.hub:5000/prj-d7te67bj0sq2fgdrmbig/sglang:recipe-ns-l3ssd-433257c7b-baked-20261115
imagePullPolicy: IfNotPresent
name: sglang
ports:
- containerPort: 30300
name: metrics
protocol: TCP
readinessProbe:
failureThreshold: 150
httpGet:
path: /health
port: metrics
initialDelaySeconds: 60
periodSeconds: 10
timeoutSeconds: 5
resources:
limits:
cpu: '96'
memory: 550Gi
nvidia.com/gpu: '4'
requests:
cpu: '32'
memory: 256Gi
nvidia.com/gpu: '4'
securityContext:
privileged: true
volumeMounts:
- mountPath: /data
name: data
- mountPath: /root/.cache/sglang
name: sglang-cache
- mountPath: /dev/shm
name: dshm
- mountPath: /root/.cargo/bin/cargo
name: fake-cargo
readOnly: true
dnsPolicy: ClusterFirstWithHostNet
hostNetwork: true
hostPID: true
nodeSelector:
kongming.io/node-group-id: ng-damg6d4grhalvvbgbbrg
kongming.io/project-id: prj-d7te67bj0sq2fgdrmbig
kubernetes.io/hostname: b300-01
volumes:
- hostPath:
path: /data
type: Directory
name: data
- hostPath:
path: /data/ymk/cache/sglang
type: Directory
name: sglang-cache
- emptyDir:
medium: Memory
sizeLimit: 64Gi
name: dshm
- hostPath:
path: /data/ymk/ds41/fake-cargo
type: File
name: fake-cargo
- dependencies:
- p
- d
minReadySeconds: 0
name: gateway
podManagementPolicy: Parallel
replicas: 1
standalonePattern:
template:
metadata:
annotations:
prometheus.io/path: /metrics
prometheus.io/port: '29000'
prometheus.io/scheme: http
prometheus.io/scrape: 'true'
labels:
app: ds41-l3ssd-gw
kongming.io/managed-by: kongming
kongming.io/node-group-id: ng-damg6d4grhalvvbgbbrg
kongming.io/project-id: prj-d7te67bj0sq2fgdrmbig
kongming.io/resource-type: custom-workload
spec:
containers:
- command:
- /bin/bash
- -c
- "exec /opt/sglang/bin/sgl-model-gateway launch \\\n --pd-disaggregation\
\ \\\n --prefill http://127.0.0.1:30000 8998 \\\n --decode http://127.0.0.1:30300\
\ \\\n --prefill-policy cache_aware --decode-policy cache_aware \\\n\
\ --g9i-enabled --g9i-max-new-tokens 4096 --g9i-est-td-enabled --g9i-shadow-enabled\
\ --g9i-td-admit enforce --g9i-p-queue-reqs-cap 32 --g9i-p-queue-token-cap\
\ 16000000 \\\n \\\n \\\n --g9i-regular-p-queue-reject-secs 0 \\\n\
\ --g9i-decode-max-running 512 \\\n --health-check-timeout-secs 30\
\ --health-check-interval-secs 30 \\\n --cb-failure-threshold 50 \\\
\n --model-path /data/models/DeepSeek-V4.1-Flash-1017 \\\n --tokenizer-path\
\ /data/models/DeepSeek-V4.1-Flash-1017 \\\n --host 0.0.0.0 --port\
\ 30400\n"
image: sealos.hub:5000/prj-d7te67bj0sq2fgdrmbig/sglang:recipe-ns-l3ssd-433257c7b-baked-20261115
imagePullPolicy: IfNotPresent
name: gateway
ports:
- containerPort: 30400
name: http
protocol: TCP
- containerPort: 29000
name: metrics
protocol: TCP
readinessProbe:
failureThreshold: 60
httpGet:
path: /health
port: http
initialDelaySeconds: 20
periodSeconds: 10
timeoutSeconds: 5
resources:
limits:
cpu: '16'
memory: 32Gi
requests:
cpu: '2'
memory: 8Gi
volumeMounts:
- mountPath: /data
name: data
- mountPath: /opt/sglang/bin/sgl-model-gateway
name: gw-bin
readOnly: true
dnsPolicy: ClusterFirstWithHostNet
hostNetwork: true
nodeSelector:
kongming.io/node-group-id: ng-damg6d4grhalvvbgbbrg
kongming.io/project-id: prj-d7te67bj0sq2fgdrmbig
kubernetes.io/hostname: b300-01
volumes:
- hostPath:
path: /data
type: Directory
name: data
- name: gw-bin
hostPath:
path: /data/ymk/gw-ns-est-td/sgl-model-gateway
type: File