feat: add GB300 MiniMax-M3 AgentX recipes / 新增 GB300 MiniMax-M3 AgentX 配置

inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/RECIPES.md

@@ -8,6 +8,8 @@ The shared version is the Git submodule pointer at [`utils/srt-slurm`](../../../
 
 InferenceX requires srt-slurm 2.0 or newer and `schema: 2` recipes. Legacy recipe layouts are unsupported; migrate them before adding them to this tree.
 
+The MiniMax-M3 Mooncake setup installs its published wheel with `--no-deps` and `--require-hashes`. It clears `UV_OVERRIDE` for that command only so unrelated image-wide package overrides do not enter the wheel's hash check. Other package installers retain the image's overrides.
+
 ## Directory and filename convention
 
 Store every recipe at `<model-prefix>/<engine>/<gpu>-<precision>/<workload>/<recipe>.yaml`:

inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/RECIPES_zh.md

@@ -8,6 +8,8 @@ InferenceX 负责维护本目录中的配置。所有 NVIDIA srt-slurm 启动器
 
 InferenceX 要求 srt-slurm 2.0 或更新版本，且配置必须声明 `schema: 2`。不支持旧版配置结构；加入本目录前必须先完成迁移。
 
+MiniMax-M3 的 Mooncake 安装脚本使用 `--no-deps` 和 `--require-hashes` 安装已发布的 wheel。仅对该命令清除 `UV_OVERRIDE`，避免镜像中无关的软件包版本覆盖项进入 wheel 的哈希校验。其他安装命令仍使用镜像的版本覆盖配置。
+
 ## 目录和文件命名规范
 
 所有配置统一存放在 `<model-prefix>/<engine>/<gpu>-<precision>/<workload>/<recipe>.yaml`：

inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/configs/minimaxm3-mooncake/setup-disagg.sh

@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+set -eo pipefail
+# Download, verify, and install the published wheel inside each backend container.
+# Image-wide overrides are unrelated to this dependency-free wheel install.
+env -u UV_OVERRIDE uv pip install --system --no-deps --reinstall --require-hashes \
+    'https://test-files.pythonhosted.org/packages/f3/00/fb2847f5564864be132d0f70384dde5688689d9f91b2c81d2609632f36e4/mooncake_transfer_engine_cuda13-0.3.14.dev20260910-cp312-cp312-manylinux_2_28_aarch64.whl#sha256=c55fcc42cf189fcdecdcdf9d776ef84b348a9970a9bd3aad2fad64cb2d9e6f82'

inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/minimaxm3/vllm/gb300-fp4/agentx/agg-tp2-c24-mtp.yaml

@@ -0,0 +1,136 @@
+schema: 2
+name: minimax-m3-gb300-agg-tp2-c24
+dynamo:
+  install: true
+  source:
+    wheel: 1.5.0.dev20260914
+  request_plane: tcp
+services:
+- name: etcd
+  type: etcd
+  placement:
+    node: infra
+- name: nats
+  type: nats
+  placement:
+    node: infra
+  options:
+    max_payload_mb: 32
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  args:
+    router-mode: least-loaded
+    router-session-affinity-ttl-secs: 14400
+  env:
+    DYN_TOKENIZER: fastokens
+    DYN_TOKENIZER_CACHE_BYTES: '8589934592'
+    DYN_TCP_CONNECT_TIMEOUT: '120'
+model:
+  path: nvidia/MiniMax-M3-NVFP4
+  container: vllm/vllm-openai:nightly-0bfc7a15d095fe83ecc82b50561a93c177fece2d@sha256:ac75d722e093a1d6b1515fdb0d9cff692225e47e8bcbaf614a1a220d302fa116
+  precision: fp4
+identity:
+  model:
+    repo: nvidia/MiniMax-M3-NVFP4
+  container:
+    image: vllm/vllm-openai:nightly-0bfc7a15d095fe83ecc82b50561a93c177fece2d@sha256:ac75d722e093a1d6b1515fdb0d9cff692225e47e8bcbaf614a1a220d302fa116
+  frameworks:
+    dynamo: 1.5.0.dev20260914
+resources:
+  gpu_type: gb300
+  gpus_per_node: 4
+engine:
+  type: vllm
+  connector: null
+  dp_launch_mode: per_gpu
+roles:
+  agg:
+    nodes: 1
+    workers: 1
+    gpus: 2
+    env:
+      VLLM_ENGINE_READY_TIMEOUT_S: '3600'
+      DYN_TCP_CONNECT_TIMEOUT: '120'
+      VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS: '1800'
+      VLLM_FLOAT32_MATMUL_PRECISION: high
+      VLLM_FLASHINFER_ALLREDUCE_BACKEND: trtllm
+      VLLM_USE_NCCL_SYMM_MEM: '0'
+      VLLM_ALLREDUCE_USE_SYMM_MEM: '0'
+      VLLM_USE_SIMPLE_KV_OFFLOAD: '1'
+      VLLM_LOG_STATS_INTERVAL: '1'
+      NCCL_CUMEM_ENABLE: '1'
+      NCCL_MNNVL_ENABLE: '1'
+      NCCL_NVLS_ENABLE: '1'
+      HF_HUB_CACHE: /hf_hub_cache
+      HUGGINGFACE_HUB_CACHE: /hf_hub_cache
+    args:
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      tensor-parallel-size: 2
+      pipeline-parallel-size: 1
+      trust-remote-code: true
+      enable-prefix-caching: true
+      kv-cache-dtype: fp8
+      block-size: 128
+      gpu-memory-utilization: 0.9
+      max-model-len: 1048576
+      language-model-only: true
+      no-enable-flashinfer-autotune: true
+      attention-config: '{"backend":"FLASHINFER","use_trtllm_attention":true,"indexer_kv_dtype":"fp8"}'
+      speculative-config: '{"method":"eagle3","model":"Inferact/MiniMax-M3-EAGLE3-GQA","num_speculative_tokens":3,"attention_backend":"FLASHINFER"}'
+      kv-transfer-config: '{"kv_connector":"SimpleCPUOffloadConnector","kv_role":"kv_both","kv_connector_extra_config":{"cpu_bytes_to_use":429496729600,"cpu_bytes_to_use_per_rank":214748364800,"lazy_offload":true}}'
+      max-cudagraph-capture-size: 512
+      max-num-batched-tokens: 16384
+      stream-interval: 20
+      reasoning-parser: minimax_m3
+      dyn-tool-call-parser: minimax_m3
+      dyn-reasoning-parser: minimax_m3
+      dyn-default-thinking-mode: enabled
+benchmark:
+  type: custom
+  use_chat_template: true
+  command: bash /infmax-workspace/benchmarks/srt_agentic.sh
+  env:
+    AIPERF_HTTP_X_DYNAMO_SESSION_ID_FROM_CORRELATION_ID: 'true'
+    AIPERF_USE_DYNAMO_CONV_AWARE_ROUTING: '0'
+    AIPERF_DYNAMO_SESSION_TIMEOUT_SECONDS: '14400'
+    ENABLE_AGENTX_POWER: '0'
+    AIPERF_EXTRA_INPUTS: thinking:true
+    AIPERF_REQUIRED_SERVER_METRIC_PREFIX: 'vllm:'
+    AIPERF_DATASET_MMAP_CACHE_DIR: /aiperf_mmap_cache
+    AIPERF_SERVER_METRICS_COLLECTION_INTERVAL: '1.0'
+    AIPERF_WARMUP_REQUESTS_PER_LANE: '10'
+    AIPERF_TRACE_IDLE_GAP_CAP_SECONDS: '300'
+    AIPERF_SERVICE_PROFILE_CONFIGURE_TIMEOUT: '1800'
+    AIPERF_DATASET_CONFIGURATION_TIMEOUT: '1800'
+    AGENTIC_WARMUP_GRACE_PERIOD: '1800'
+    AIPERF_DRAIN_TIMEOUT_SECONDS: '1800'
+    AIPERF_TIMING_CANCEL_DRAIN_TIMEOUT: '300'
+    INFMAX_CONTAINER_WORKSPACE: /infmax-workspace
+    RESULT_DIR: /logs/agentic
+    PORT: '8000'
+    TP: '2'
+    EP_SIZE: '1'
+    IS_MULTINODE: 'false'
+    DISAGG: 'false'
+    HF_HUB_CACHE: /hf_hub_cache
+    WEKA_LOADER_OVERRIDE: semianalysis_cc_traces_weka_062126
+observability:
+  tachometer:
+    enabled: false
+telemetry:
+  enabled: false
+health_check:
+  max_attempts: 2160
+  interval_seconds: 10
+sbatch_directives:
+  cpus-per-task: '144'
+  mem: '0'
+srun_options:
+  container-remap-root: ''
+  cpu-bind: cores
+slurm:
+  time_limit: '8:00:00'
+environment:
+  PYTHONHASHSEED: '0'
+  WITH_NVIDIA_PEERMEM: '0'

inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/minimaxm3/vllm/gb300-fp4/agentx/agg-tp8-c1-mtp.yaml

@@ -0,0 +1,138 @@
+schema: 2
+name: minimax-m3-gb300-agg-tp8-c1
+dynamo:
+  install: true
+  source:
+    wheel: 1.5.0.dev20260914
+  request_plane: tcp
+services:
+- name: etcd
+  type: etcd
+  placement:
+    node: infra
+- name: nats
+  type: nats
+  placement:
+    node: infra
+  options:
+    max_payload_mb: 32
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  args:
+    router-mode: least-loaded
+    router-session-affinity-ttl-secs: 14400
+  env:
+    DYN_TOKENIZER: fastokens
+    DYN_TOKENIZER_CACHE_BYTES: '8589934592'
+    DYN_TCP_CONNECT_TIMEOUT: '120'
+model:
+  path: nvidia/MiniMax-M3-NVFP4
+  container: vllm/vllm-openai:nightly-0bfc7a15d095fe83ecc82b50561a93c177fece2d@sha256:ac75d722e093a1d6b1515fdb0d9cff692225e47e8bcbaf614a1a220d302fa116
+  precision: fp4
+identity:
+  model:
+    repo: nvidia/MiniMax-M3-NVFP4
+  container:
+    image: vllm/vllm-openai:nightly-0bfc7a15d095fe83ecc82b50561a93c177fece2d@sha256:ac75d722e093a1d6b1515fdb0d9cff692225e47e8bcbaf614a1a220d302fa116
+  frameworks:
+    dynamo: 1.5.0.dev20260914
+resources:
+  gpu_type: gb300
+  gpus_per_node: 4
+engine:
+  type: vllm
+  connector: null
+  dp_launch_mode: per_gpu
+roles:
+  agg:
+    nodes: 2
+    workers: 1
+    gpus: 8
+    env:
+      VLLM_ENGINE_READY_TIMEOUT_S: '3600'
+      DYN_TCP_CONNECT_TIMEOUT: '120'
+      VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS: '1800'
+      VLLM_FLOAT32_MATMUL_PRECISION: high
+      VLLM_FLASHINFER_ALLREDUCE_BACKEND: mnnvl
+      VLLM_USE_NCCL_SYMM_MEM: '0'
+      VLLM_ALLREDUCE_USE_SYMM_MEM: '0'
+      VLLM_LOG_STATS_INTERVAL: '1'
+      UCX_MEMTYPE_CACHE: n
+      UCX_NET_DEVICES: mlx5_0:1,mlx5_1:1,mlx5_2:1,mlx5_3:1
+      UCX_TLS: rc,cuda_copy
+      NCCL_CUMEM_ENABLE: '1'
+      NCCL_MNNVL_ENABLE: '1'
+      NCCL_NVLS_ENABLE: '1'
+      NCCL_IB_HCA: mlx5_0,mlx5_1,mlx5_2,mlx5_3
+      HF_HUB_CACHE: /hf_hub_cache
+      HUGGINGFACE_HUB_CACHE: /hf_hub_cache
+    args:
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      tensor-parallel-size: 8
+      pipeline-parallel-size: 1
+      trust-remote-code: true
+      enable-prefix-caching: true
+      kv-cache-dtype: fp8
+      block-size: 128
+      gpu-memory-utilization: 0.9
+      max-model-len: 1048576
+      language-model-only: true
+      no-enable-flashinfer-autotune: true
+      attention-config: '{"backend":"FLASHINFER","use_trtllm_attention":true,"indexer_kv_dtype":"fp8"}'
+      speculative-config: '{"method":"eagle3","model":"Inferact/MiniMax-M3-EAGLE3-GQA","num_speculative_tokens":3,"attention_backend":"FLASHINFER"}'
+      max-cudagraph-capture-size: 512
+      max-num-batched-tokens: 16384
+      stream-interval: 20
+      reasoning-parser: minimax_m3
+      dyn-tool-call-parser: minimax_m3
+      dyn-reasoning-parser: minimax_m3
+      dyn-default-thinking-mode: enabled
+benchmark:
+  type: custom
+  use_chat_template: true
+  command: bash /infmax-workspace/benchmarks/srt_agentic.sh
+  env:
+    AIPERF_HTTP_X_DYNAMO_SESSION_ID_FROM_CORRELATION_ID: 'true'
+    AIPERF_USE_DYNAMO_CONV_AWARE_ROUTING: '0'
+    AIPERF_DYNAMO_SESSION_TIMEOUT_SECONDS: '14400'
+    ENABLE_AGENTX_POWER: '0'
+    AIPERF_EXTRA_INPUTS: thinking:true
+    AIPERF_REQUIRED_SERVER_METRIC_PREFIX: 'vllm:'
+    AIPERF_DATASET_MMAP_CACHE_DIR: /aiperf_mmap_cache
+    AIPERF_SERVER_METRICS_COLLECTION_INTERVAL: '1.0'
+    AIPERF_WARMUP_REQUESTS_PER_LANE: '10'
+    AIPERF_TRACE_IDLE_GAP_CAP_SECONDS: '300'
+    AIPERF_SERVICE_PROFILE_CONFIGURE_TIMEOUT: '1800'
+    AIPERF_DATASET_CONFIGURATION_TIMEOUT: '1800'
+    AGENTIC_WARMUP_GRACE_PERIOD: '1800'
+    AIPERF_DRAIN_TIMEOUT_SECONDS: '1800'
+    AIPERF_TIMING_CANCEL_DRAIN_TIMEOUT: '300'
+    INFMAX_CONTAINER_WORKSPACE: /infmax-workspace
+    RESULT_DIR: /logs/agentic
+    PORT: '8000'
+    TP: '8'
+    EP_SIZE: '1'
+    IS_MULTINODE: 'false'
+    DISAGG: 'false'
+    HF_HUB_CACHE: /hf_hub_cache
+    WEKA_LOADER_OVERRIDE: semianalysis_cc_traces_weka_062126
+observability:
+  tachometer:
+    enabled: false
+telemetry:
+  enabled: false
+health_check:
+  max_attempts: 2160
+  interval_seconds: 10
+sbatch_directives:
+  cpus-per-task: '144'
+  mem: '0'
+srun_options:
+  container-remap-root: ''
+  cpu-bind: cores
+slurm:
+  time_limit: '8:00:00'
+environment:
+  PYTHONHASHSEED: '0'
+  WITH_NVIDIA_PEERMEM: '0'