[NV] Refresh GB300 DeepSeek-V4-Pro AgentX with SGLang DSpark6 / 使用 SGLang DSpark6 更新 GB300 DeepSeek-V4-Pro AgentX

benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/agentic/agg-gb300-tp4-mtp-lowlatency.yaml

@@ -0,0 +1,120 @@
+name: "agg-gb300-tp4-mtp-lowlatency"
+
+# Low-latency AgentX aggregate topology: one TP4 worker occupies one
+# four-GPU GB300 node and serves both prefill and decode with DSpark K=6.
+
+model:
+  path: "deepseek-v4-pro-0813"
+  container: "dynamo-sglang"
+  precision: "fp4"
+
+identity:
+  model:
+    repo: "deepseek-ai/DeepSeek-V4-Pro-0813"
+  container:
+    image: "lmsysorg/sglang:nightly-dev-cu13-20260816-4a6dc267"
+
+dynamo:
+  install: true
+  hash: "7a4e47ead90ec6b479e397996f6479ce7d251510"
+
+slurm:
+  time_limit: "4:00:00"
+
+health_check:
+  max_attempts: 1440
+  interval_seconds: 10
+
+resources:
+  gpu_type: "gb300"
+  gpus_per_node: 4
+  agg_nodes: 1
+  agg_workers: 1
+  gpus_per_agg: 4
+
+infra:
+  etcd_nats_dedicated_node: false
+  nats_max_payload_mb: 32
+
+frontend:
+  type: dynamo
+  nginx_session_affinity: true
+  nginx_session_affinity_header: X-Dynamo-Session-ID
+  enable_multiple_frontends: false
+  env:
+    PIP_BREAK_SYSTEM_PACKAGES: "1"
+    DYN_NATS_REQUEST_TIMEOUT_SECS: "1800"
+  args:
+    router-mode: "kv"
+    router-session-affinity-ttl-secs: "3600"
+    active-decode-blocks-threshold: "None"
+    active-prefill-tokens-threshold: "None"
+    active-prefill-tokens-threshold-frac: "None"
+
+backend:
+  type: sglang
+  aggregated_environment:
+    SGLANG_RAGGED_VERIFY_MODE: "static"
+    SGLANG_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: high
+    PIP_BREAK_SYSTEM_PACKAGES: "1"
+    SGLANG_JIT_DEEPGEMM_PRECOMPILE: "1"
+    # Avoid the TP4 DSpark startup stall in the shared-read-done fastpath.
+    SGLANG_FORCE_COARSE_WAR_BARRIER: "1"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_UNIFIED_CACHE_FREE_OUT_OF_WINDOW_SLOTS: "1"
+    SGLANG_OPT_USE_CUSTOM_ALL_REDUCE_V2: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "0"
+    SGLANG_OPT_USE_JIT_INDEXER_METADATA: "1"
+    SGLANG_OPT_USE_JIT_NORM: "1"
+    SGLANG_OPT_USE_TOPK_V2: "True"
+
+  sglang_config:
+    aggregated:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro-0813"
+      enable-metrics: true
+      enable-cache-report: true
+      trust-remote-code: true
+      weight-loader-prefetch-checkpoints: true
+      stream-interval: 10
+      watchdog-timeout: 1000000
+      mem-fraction-static: 0.94
+      chunked-prefill-size: 8192
+      max-prefill-tokens: 8192
+      moe-runner-backend: "flashinfer_mxfp4"
+      disable-flashinfer-autotune: true
+      swa-full-tokens-ratio: 0.1
+      max-running-requests: 32
+      cuda-graph-max-bs-decode: 32
+      scheduler-recv-interval: 30
+      dp-size: 1
+      tp-size: 4
+      ep-size: 1
+      speculative-algorithm: DSPARK
+      speculative-dspark-block-size: 6
+      speculative-num-steps: 1
+      speculative-eagle-topk: 1
+      speculative-num-draft-tokens: 7
+
+sbatch_directives:
+  mem: "0"
+  cpus-per-task: "144"
+
+srun_options:
+  mem: "0"
+  container-remap-root: ""
+
+benchmark:
+  type: custom
+  command: bash /infmax-workspace/benchmarks/multi_node/agentic_srt.sh
+  env:
+    INFMAX_CONTAINER_WORKSPACE: "/infmax-workspace"
+    RESULT_DIR: "/logs/agentic"
+    PORT: "8000"
+    IS_MULTINODE: "false"
+    TP: "4"
+    AIPERF_HTTP_X_DYNAMO_SESSION_ID_FROM_CORRELATION_ID: "true"
+    AIPERF_USE_DYNAMO_CONV_AWARE_ROUTING: "0"
+    AIPERF_REQUIRED_SERVER_METRIC_PREFIX: "sglang:"
+    AIPERF_DATASET_MMAP_CACHE_DIR: "/aiperf_mmap_cache"
+    HF_HUB_CACHE: "/hf_hub_cache"

benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/agentic/agg-gb300-tp8-mtp-lowlatency.yaml

@@ -0,0 +1,120 @@
+name: "agg-gb300-tp8-mtp-lowlatency"
+
+# Low-latency AgentX aggregate topology: one TP8 worker spans two
+# four-GPU GB300 nodes and serves both prefill and decode with DSpark K=6.
+
+model:
+  path: "deepseek-v4-pro-0813"
+  container: "dynamo-sglang"
+  precision: "fp4"
+
+identity:
+  model:
+    repo: "deepseek-ai/DeepSeek-V4-Pro-0813"
+  container:
+    image: "lmsysorg/sglang:nightly-dev-cu13-20260816-4a6dc267"
+
+dynamo:
+  install: true
+  hash: "7a4e47ead90ec6b479e397996f6479ce7d251510"
+
+slurm:
+  time_limit: "4:00:00"
+
+health_check:
+  max_attempts: 1440
+  interval_seconds: 10
+
+resources:
+  gpu_type: "gb300"
+  gpus_per_node: 4
+  agg_nodes: 2
+  agg_workers: 1
+  gpus_per_agg: 8
+
+infra:
+  etcd_nats_dedicated_node: false
+  nats_max_payload_mb: 32
+
+frontend:
+  type: dynamo
+  nginx_session_affinity: true
+  nginx_session_affinity_header: X-Dynamo-Session-ID
+  enable_multiple_frontends: false
+  env:
+    PIP_BREAK_SYSTEM_PACKAGES: "1"
+    DYN_NATS_REQUEST_TIMEOUT_SECS: "1800"
+  args:
+    router-mode: "kv"
+    router-session-affinity-ttl-secs: "3600"
+    active-decode-blocks-threshold: "None"
+    active-prefill-tokens-threshold: "None"
+    active-prefill-tokens-threshold-frac: "None"
+
+backend:
+  type: sglang
+  aggregated_environment:
+    SGLANG_RAGGED_VERIFY_MODE: "static"
+    # Avoid aggregate DSpark startup stalls in the shared-read-done fastpath.
+    SGLANG_FORCE_COARSE_WAR_BARRIER: "1"
+    SGLANG_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: high
+    PIP_BREAK_SYSTEM_PACKAGES: "1"
+    SGLANG_JIT_DEEPGEMM_PRECOMPILE: "1"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_UNIFIED_CACHE_FREE_OUT_OF_WINDOW_SLOTS: "1"
+    SGLANG_OPT_USE_CUSTOM_ALL_REDUCE_V2: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "0"
+    SGLANG_OPT_USE_JIT_INDEXER_METADATA: "1"
+    SGLANG_OPT_USE_JIT_NORM: "1"
+    SGLANG_OPT_USE_TOPK_V2: "True"
+
+  sglang_config:
+    aggregated:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro-0813"
+      enable-metrics: true
+      enable-cache-report: true
+      trust-remote-code: true
+      weight-loader-prefetch-checkpoints: true
+      stream-interval: 10
+      watchdog-timeout: 1000000
+      mem-fraction-static: 0.94
+      chunked-prefill-size: 8192
+      max-prefill-tokens: 8192
+      moe-runner-backend: "flashinfer_mxfp4"
+      disable-flashinfer-autotune: true
+      swa-full-tokens-ratio: 0.1
+      max-running-requests: 4
+      cuda-graph-max-bs-decode: 4
+      scheduler-recv-interval: 30
+      dp-size: 1
+      tp-size: 8
+      ep-size: 1
+      speculative-algorithm: DSPARK
+      speculative-dspark-block-size: 6
+      speculative-num-steps: 1
+      speculative-eagle-topk: 1
+      speculative-num-draft-tokens: 7
+
+sbatch_directives:
+  mem: "0"
+  cpus-per-task: "144"
+
+srun_options:
+  mem: "0"
+  container-remap-root: ""
+
+benchmark:
+  type: custom
+  command: bash /infmax-workspace/benchmarks/multi_node/agentic_srt.sh
+  env:
+    INFMAX_CONTAINER_WORKSPACE: "/infmax-workspace"
+    RESULT_DIR: "/logs/agentic"
+    PORT: "8000"
+    IS_MULTINODE: "false"
+    TP: "8"
+    AIPERF_HTTP_X_DYNAMO_SESSION_ID_FROM_CORRELATION_ID: "true"
+    AIPERF_USE_DYNAMO_CONV_AWARE_ROUTING: "0"
+    AIPERF_REQUIRED_SERVER_METRIC_PREFIX: "sglang:"
+    AIPERF_DATASET_MMAP_CACHE_DIR: "/aiperf_mmap_cache"
+    HF_HUB_CACHE: "/hf_hub_cache"