diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/1p1d-dep2-tp4-c1-c16-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/1p1d-dep2-tp4-c1-c16-8k1k.yaml
new file mode 100644
index 000000000..dfbe048f1
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/1p1d-dep2-tp4-c1-c16-8k1k.yaml
@@ -0,0 +1,62 @@
+name: "minimax-m3-vllm-disagg-b200-1p1d-fp4-dep2-tp4-8k1k"
+model:
+  path: "nvidia/MiniMax-M3-NVFP4"
+  container: "vllm/vllm-openai:cu129-nightly-8e981630c9336233ca9de91452f68918bddbc4e2"
+  precision: "fp4"
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 1
+  decode_nodes: 1
+  prefill_workers: 1
+  decode_workers: 1
+  gpus_per_prefill: 2
+  gpus_per_decode: 4
+dynamo: {install: true, version: 1.2.1}
+frontend: {type: dynamo, enable_multiple_frontends: false}
+backend:
+  type: vllm
+  connector: null
+  allow_prefill_decode_colocation: true
+  prefill_environment: {VLLM_FLOAT32_MATMUL_PRECISION: high, UCX_TLS: "cuda_ipc,cuda_copy,rc"}
+  decode_environment: {VLLM_FLOAT32_MATMUL_PRECISION: high, UCX_TLS: "cuda_ipc,cuda_copy,rc"}
+  vllm_config:
+    prefill:
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      tensor-parallel-size: 1
+      data-parallel-size: 2
+      data-parallel-rpc-port: 13345
+      enable-expert-parallel: true
+      trust-remote-code: true
+      no-enable-prefix-caching: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      kv-cache-dtype: fp8
+      block-size: 128
+      gpu-memory-utilization: 0.90
+      max-model-len: 9472
+      language-model-only: true
+      stream-interval: 32
+      max-cudagraph-capture-size: 2048
+      max-num-batched-tokens: 16384
+    decode:
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      tensor-parallel-size: 4
+      enable-expert-parallel: false
+      trust-remote-code: true
+      no-enable-prefix-caching: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      kv-cache-dtype: fp8
+      block-size: 128
+      gpu-memory-utilization: 0.90
+      max-model-len: 9472
+      language-model-only: true
+      stream-interval: 32
+      max-num-seqs: 1024
+      max-num-batched-tokens: 16384
+      max-cudagraph-capture-size: 2048
+health_check: {max_attempts: 360, interval_seconds: 10}
+benchmark: {type: "sa-bench", isl: 8192, osl: 1024, random_range_ratio: 0.8, concurrencies: "1x4x8x16", req_rate: "inf"}
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/1p2d-dep2-tp4-c64-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/1p2d-dep2-tp4-c64-8k1k.yaml
new file mode 100644
index 000000000..8b887b3bf
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/1p2d-dep2-tp4-c64-8k1k.yaml
@@ -0,0 +1,127 @@
+name: minimax-m3-vllm-disagg-b200-1p2d-fp4-dep2-tp4-c64-8k1k
+model:
+  path: nvidia/MiniMax-M3-NVFP4
+  container: vllm/vllm-openai:cu129-nightly-8e981630c9336233ca9de91452f68918bddbc4e2
+  precision: fp4
+resources:
+  gpu_type: b200
+  prefill_nodes: 1
+  prefill_workers: 1
+  gpus_per_prefill: 2
+  decode_nodes: 2
+  decode_workers: 2
+  spread_workers: true
+  gpus_per_decode: 4
+  gpus_per_node: 8
+backend:
+  type: vllm
+  connector: null
+  prefill_environment:
+    VLLM_USE_DEEP_GEMM: '1'
+    VLLM_SKIP_P2P_CHECK: '1'
+    VLLM_RANDOMIZE_DP_DUMMY_INPUTS: '1'
+    NVIDIA_GDRCOPY: '1'
+    PYTHONUNBUFFERED: '1'
+    VLLM_LOG_STATS_INTERVAL: '1'
+    NVSHMEM_IB_ENABLE_IBGDA: '1'
+    NCCL_CUMEM_ENABLE: '1'
+    NCCL_MNNVL_ENABLE: '1'
+    NCCL_NVLS_ENABLE: '1'
+    NCCL_TIMEOUT: '1800'
+    TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC: '1800'
+    VLLM_USE_FLASHINFER_MOE_FP4: '1'
+    VLLM_USE_TRTLLM_RAGGED_DEEPSEEK_PREFILL: '0'
+    VLLM_USE_NCCL_SYMM_MEM: '1'
+    UCX_IB_ROCE_REACHABILITY_MODE: local_subnet
+    VLLM_NIXL_SIDE_CHANNEL_PORT: '5600'
+    VLLM_NIXL_ABORT_REQUEST_TIMEOUT: '300'
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: cuda_ipc,cuda_copy,rc
+  decode_environment:
+    VLLM_USE_DEEP_GEMM: '1'
+    VLLM_SKIP_P2P_CHECK: '1'
+    VLLM_RANDOMIZE_DP_DUMMY_INPUTS: '1'
+    NVIDIA_GDRCOPY: '1'
+    PYTHONUNBUFFERED: '1'
+    VLLM_LOG_STATS_INTERVAL: '1'
+    NVSHMEM_IB_ENABLE_IBGDA: '1'
+    NCCL_CUMEM_ENABLE: '1'
+    NCCL_MNNVL_ENABLE: '1'
+    NCCL_NVLS_ENABLE: '1'
+    NCCL_TIMEOUT: '1800'
+    TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC: '1800'
+    VLLM_USE_FLASHINFER_MOE_FP4: '1'
+    VLLM_USE_TRTLLM_RAGGED_DEEPSEEK_PREFILL: '0'
+    VLLM_USE_NCCL_SYMM_MEM: '1'
+    UCX_IB_ROCE_REACHABILITY_MODE: local_subnet
+    VLLM_NIXL_SIDE_CHANNEL_PORT: '5600'
+    VLLM_NIXL_ABORT_REQUEST_TIMEOUT: '300'
+    VLLM_MOE_DP_CHUNK_SIZE: '384'
+    VLLM_SHARED_EXPERTS_STREAM_TOKEN_THRESHOLD: '8192'
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: cuda_ipc,cuda_copy,rc
+  vllm_config:
+    prefill:
+      tensor-parallel-size: 1
+      pipeline-parallel-size: 1
+      enable-expert-parallel: true
+      data-parallel-size: 2
+      data-parallel-rpc-port: 13345
+      data-parallel-hybrid-lb: true
+      max-model-len: 9472
+      max-num-seqs: 16
+      enforce-eager: true
+      gpu-memory-utilization: 0.9
+      max-num-batched-tokens: 16384
+      no-enable-chunked-prefill: true
+      kv-cache-dtype: fp8
+      async-scheduling: true
+      no-enable-prefix-caching: true
+      trust-remote-code: true
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      block-size: 128
+      language-model-only: true
+      stream-interval: 32
+      max-cudagraph-capture-size: 2048
+    decode:
+      tensor-parallel-size: 4
+      pipeline-parallel-size: 1
+      enable-expert-parallel: false
+      max-model-len: 9472
+      max-num-seqs: 32
+      gpu-memory-utilization: 0.9
+      max-num-batched-tokens: 16384
+      max-cudagraph-capture-size: 2048
+      compilation-config: '{"cudagraph_mode":"FULL_DECODE_ONLY","custom_ops":["+rms_norm"],"pass_config":{}}'
+      kv-cache-dtype: fp8
+      all2all-backend: deepep_low_latency
+      async-scheduling: true
+      stream-interval: 32
+      enable-dbo: true
+      dbo-decode-token-threshold: 32
+      no-enable-prefix-caching: true
+      trust-remote-code: true
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      block-size: 128
+      language-model-only: true
+benchmark:
+  type: sa-bench
+  isl: 8192
+  osl: 1024
+  concurrencies: '64'
+  req_rate: inf
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  args:
+    dyn-chat-processor: vllm
+    reasoning-parser: minimax_m3
+dynamo:
+  install: false
+  version: 1.2.1
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/2p2d-dep2-tp4-c128-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/2p2d-dep2-tp4-c128-8k1k.yaml
new file mode 100644
index 000000000..f1014157d
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/2p2d-dep2-tp4-c128-8k1k.yaml
@@ -0,0 +1,127 @@
+name: minimax-m3-vllm-disagg-b200-2p2d-fp4-dep2-tp4-c128-8k1k
+model:
+  path: nvidia/MiniMax-M3-NVFP4
+  container: vllm/vllm-openai:cu129-nightly-8e981630c9336233ca9de91452f68918bddbc4e2
+  precision: fp4
+resources:
+  gpu_type: b200
+  prefill_nodes: 1
+  prefill_workers: 2
+  gpus_per_prefill: 2
+  decode_nodes: 2
+  decode_workers: 2
+  spread_workers: true
+  gpus_per_decode: 4
+  gpus_per_node: 8
+backend:
+  type: vllm
+  connector: null
+  prefill_environment:
+    VLLM_USE_DEEP_GEMM: '1'
+    VLLM_SKIP_P2P_CHECK: '1'
+    VLLM_RANDOMIZE_DP_DUMMY_INPUTS: '1'
+    NVIDIA_GDRCOPY: '1'
+    PYTHONUNBUFFERED: '1'
+    VLLM_LOG_STATS_INTERVAL: '1'
+    NVSHMEM_IB_ENABLE_IBGDA: '1'
+    NCCL_CUMEM_ENABLE: '1'
+    NCCL_MNNVL_ENABLE: '1'
+    NCCL_NVLS_ENABLE: '1'
+    NCCL_TIMEOUT: '1800'
+    TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC: '1800'
+    VLLM_USE_FLASHINFER_MOE_FP4: '1'
+    VLLM_USE_TRTLLM_RAGGED_DEEPSEEK_PREFILL: '0'
+    VLLM_USE_NCCL_SYMM_MEM: '1'
+    UCX_IB_ROCE_REACHABILITY_MODE: local_subnet
+    VLLM_NIXL_SIDE_CHANNEL_PORT: '5600'
+    VLLM_NIXL_ABORT_REQUEST_TIMEOUT: '300'
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: cuda_ipc,cuda_copy,rc
+  decode_environment:
+    VLLM_USE_DEEP_GEMM: '1'
+    VLLM_SKIP_P2P_CHECK: '1'
+    VLLM_RANDOMIZE_DP_DUMMY_INPUTS: '1'
+    NVIDIA_GDRCOPY: '1'
+    PYTHONUNBUFFERED: '1'
+    VLLM_LOG_STATS_INTERVAL: '1'
+    NVSHMEM_IB_ENABLE_IBGDA: '1'
+    NCCL_CUMEM_ENABLE: '1'
+    NCCL_MNNVL_ENABLE: '1'
+    NCCL_NVLS_ENABLE: '1'
+    NCCL_TIMEOUT: '1800'
+    TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC: '1800'
+    VLLM_USE_FLASHINFER_MOE_FP4: '1'
+    VLLM_USE_TRTLLM_RAGGED_DEEPSEEK_PREFILL: '0'
+    VLLM_USE_NCCL_SYMM_MEM: '1'
+    UCX_IB_ROCE_REACHABILITY_MODE: local_subnet
+    VLLM_NIXL_SIDE_CHANNEL_PORT: '5600'
+    VLLM_NIXL_ABORT_REQUEST_TIMEOUT: '300'
+    VLLM_MOE_DP_CHUNK_SIZE: '384'
+    VLLM_SHARED_EXPERTS_STREAM_TOKEN_THRESHOLD: '8192'
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: cuda_ipc,cuda_copy,rc
+  vllm_config:
+    prefill:
+      tensor-parallel-size: 1
+      pipeline-parallel-size: 1
+      enable-expert-parallel: true
+      data-parallel-size: 2
+      data-parallel-rpc-port: 13345
+      data-parallel-hybrid-lb: true
+      max-model-len: 9472
+      max-num-seqs: 16
+      enforce-eager: true
+      gpu-memory-utilization: 0.9
+      max-num-batched-tokens: 16384
+      no-enable-chunked-prefill: true
+      kv-cache-dtype: fp8
+      async-scheduling: true
+      no-enable-prefix-caching: true
+      trust-remote-code: true
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      block-size: 128
+      language-model-only: true
+      stream-interval: 32
+      max-cudagraph-capture-size: 2048
+    decode:
+      tensor-parallel-size: 4
+      pipeline-parallel-size: 1
+      enable-expert-parallel: false
+      max-model-len: 9472
+      max-num-seqs: 64
+      gpu-memory-utilization: 0.9
+      max-num-batched-tokens: 16384
+      max-cudagraph-capture-size: 2048
+      compilation-config: '{"cudagraph_mode":"FULL_DECODE_ONLY","custom_ops":["+rms_norm"],"pass_config":{}}'
+      kv-cache-dtype: fp8
+      all2all-backend: deepep_low_latency
+      async-scheduling: true
+      stream-interval: 32
+      enable-dbo: true
+      dbo-decode-token-threshold: 32
+      no-enable-prefix-caching: true
+      trust-remote-code: true
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      block-size: 128
+      language-model-only: true
+benchmark:
+  type: sa-bench
+  isl: 8192
+  osl: 1024
+  concurrencies: '128'
+  req_rate: inf
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  args:
+    dyn-chat-processor: vllm
+    reasoning-parser: minimax_m3
+dynamo:
+  install: false
+  version: 1.2.1
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/3p2d-dep2-tp4-c256-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/3p2d-dep2-tp4-c256-8k1k.yaml
new file mode 100644
index 000000000..7becb72ab
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/3p2d-dep2-tp4-c256-8k1k.yaml
@@ -0,0 +1,127 @@
+name: minimax-m3-vllm-disagg-b200-3p2d-fp4-dep2-tp4-c256-8k1k
+model:
+  path: nvidia/MiniMax-M3-NVFP4
+  container: vllm/vllm-openai:cu129-nightly-8e981630c9336233ca9de91452f68918bddbc4e2
+  precision: fp4
+resources:
+  gpu_type: b200
+  prefill_nodes: 1
+  prefill_workers: 3
+  gpus_per_prefill: 2
+  decode_nodes: 2
+  decode_workers: 2
+  spread_workers: true
+  gpus_per_decode: 4
+  gpus_per_node: 8
+backend:
+  type: vllm
+  connector: null
+  prefill_environment:
+    VLLM_USE_DEEP_GEMM: '1'
+    VLLM_SKIP_P2P_CHECK: '1'
+    VLLM_RANDOMIZE_DP_DUMMY_INPUTS: '1'
+    NVIDIA_GDRCOPY: '1'
+    PYTHONUNBUFFERED: '1'
+    VLLM_LOG_STATS_INTERVAL: '1'
+    NVSHMEM_IB_ENABLE_IBGDA: '1'
+    NCCL_CUMEM_ENABLE: '1'
+    NCCL_MNNVL_ENABLE: '1'
+    NCCL_NVLS_ENABLE: '1'
+    NCCL_TIMEOUT: '1800'
+    TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC: '1800'
+    VLLM_USE_FLASHINFER_MOE_FP4: '1'
+    VLLM_USE_TRTLLM_RAGGED_DEEPSEEK_PREFILL: '0'
+    VLLM_USE_NCCL_SYMM_MEM: '1'
+    UCX_IB_ROCE_REACHABILITY_MODE: local_subnet
+    VLLM_NIXL_SIDE_CHANNEL_PORT: '5600'
+    VLLM_NIXL_ABORT_REQUEST_TIMEOUT: '300'
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: cuda_ipc,cuda_copy,rc
+  decode_environment:
+    VLLM_USE_DEEP_GEMM: '1'
+    VLLM_SKIP_P2P_CHECK: '1'
+    VLLM_RANDOMIZE_DP_DUMMY_INPUTS: '1'
+    NVIDIA_GDRCOPY: '1'
+    PYTHONUNBUFFERED: '1'
+    VLLM_LOG_STATS_INTERVAL: '1'
+    NVSHMEM_IB_ENABLE_IBGDA: '1'
+    NCCL_CUMEM_ENABLE: '1'
+    NCCL_MNNVL_ENABLE: '1'
+    NCCL_NVLS_ENABLE: '1'
+    NCCL_TIMEOUT: '1800'
+    TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC: '1800'
+    VLLM_USE_FLASHINFER_MOE_FP4: '1'
+    VLLM_USE_TRTLLM_RAGGED_DEEPSEEK_PREFILL: '0'
+    VLLM_USE_NCCL_SYMM_MEM: '1'
+    UCX_IB_ROCE_REACHABILITY_MODE: local_subnet
+    VLLM_NIXL_SIDE_CHANNEL_PORT: '5600'
+    VLLM_NIXL_ABORT_REQUEST_TIMEOUT: '300'
+    VLLM_MOE_DP_CHUNK_SIZE: '384'
+    VLLM_SHARED_EXPERTS_STREAM_TOKEN_THRESHOLD: '8192'
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: cuda_ipc,cuda_copy,rc
+  vllm_config:
+    prefill:
+      tensor-parallel-size: 1
+      pipeline-parallel-size: 1
+      enable-expert-parallel: true
+      data-parallel-size: 2
+      data-parallel-rpc-port: 13345
+      data-parallel-hybrid-lb: true
+      max-model-len: 9472
+      max-num-seqs: 16
+      enforce-eager: true
+      gpu-memory-utilization: 0.9
+      max-num-batched-tokens: 16384
+      no-enable-chunked-prefill: true
+      kv-cache-dtype: fp8
+      async-scheduling: true
+      no-enable-prefix-caching: true
+      trust-remote-code: true
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      block-size: 128
+      language-model-only: true
+      stream-interval: 32
+      max-cudagraph-capture-size: 2048
+    decode:
+      tensor-parallel-size: 4
+      pipeline-parallel-size: 1
+      enable-expert-parallel: false
+      max-model-len: 9472
+      max-num-seqs: 128
+      gpu-memory-utilization: 0.9
+      max-num-batched-tokens: 16384
+      max-cudagraph-capture-size: 2048
+      compilation-config: '{"cudagraph_mode":"FULL_DECODE_ONLY","custom_ops":["+rms_norm"],"pass_config":{}}'
+      kv-cache-dtype: fp8
+      all2all-backend: deepep_low_latency
+      async-scheduling: true
+      stream-interval: 32
+      enable-dbo: true
+      dbo-decode-token-threshold: 32
+      no-enable-prefix-caching: true
+      trust-remote-code: true
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      block-size: 128
+      language-model-only: true
+benchmark:
+  type: sa-bench
+  isl: 8192
+  osl: 1024
+  concurrencies: '256'
+  req_rate: inf
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  args:
+    dyn-chat-processor: vllm
+    reasoning-parser: minimax_m3
+dynamo:
+  install: false
+  version: 1.2.1
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/3p2d-dep2-tp4-c512-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/3p2d-dep2-tp4-c512-8k1k.yaml
new file mode 100644
index 000000000..25d4e5dba
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/3p2d-dep2-tp4-c512-8k1k.yaml
@@ -0,0 +1,127 @@
+name: minimax-m3-vllm-disagg-b200-3p2d-fp4-dep2-tp4-c512-8k1k
+model:
+  path: nvidia/MiniMax-M3-NVFP4
+  container: vllm/vllm-openai:cu129-nightly-8e981630c9336233ca9de91452f68918bddbc4e2
+  precision: fp4
+resources:
+  gpu_type: b200
+  prefill_nodes: 1
+  prefill_workers: 3
+  gpus_per_prefill: 2
+  decode_nodes: 2
+  decode_workers: 2
+  spread_workers: true
+  gpus_per_decode: 4
+  gpus_per_node: 8
+backend:
+  type: vllm
+  connector: null
+  prefill_environment:
+    VLLM_USE_DEEP_GEMM: '1'
+    VLLM_SKIP_P2P_CHECK: '1'
+    VLLM_RANDOMIZE_DP_DUMMY_INPUTS: '1'
+    NVIDIA_GDRCOPY: '1'
+    PYTHONUNBUFFERED: '1'
+    VLLM_LOG_STATS_INTERVAL: '1'
+    NVSHMEM_IB_ENABLE_IBGDA: '1'
+    NCCL_CUMEM_ENABLE: '1'
+    NCCL_MNNVL_ENABLE: '1'
+    NCCL_NVLS_ENABLE: '1'
+    NCCL_TIMEOUT: '1800'
+    TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC: '1800'
+    VLLM_USE_FLASHINFER_MOE_FP4: '1'
+    VLLM_USE_TRTLLM_RAGGED_DEEPSEEK_PREFILL: '0'
+    VLLM_USE_NCCL_SYMM_MEM: '1'
+    UCX_IB_ROCE_REACHABILITY_MODE: local_subnet
+    VLLM_NIXL_SIDE_CHANNEL_PORT: '5600'
+    VLLM_NIXL_ABORT_REQUEST_TIMEOUT: '300'
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: cuda_ipc,cuda_copy,rc
+  decode_environment:
+    VLLM_USE_DEEP_GEMM: '1'
+    VLLM_SKIP_P2P_CHECK: '1'
+    VLLM_RANDOMIZE_DP_DUMMY_INPUTS: '1'
+    NVIDIA_GDRCOPY: '1'
+    PYTHONUNBUFFERED: '1'
+    VLLM_LOG_STATS_INTERVAL: '1'
+    NVSHMEM_IB_ENABLE_IBGDA: '1'
+    NCCL_CUMEM_ENABLE: '1'
+    NCCL_MNNVL_ENABLE: '1'
+    NCCL_NVLS_ENABLE: '1'
+    NCCL_TIMEOUT: '1800'
+    TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC: '1800'
+    VLLM_USE_FLASHINFER_MOE_FP4: '1'
+    VLLM_USE_TRTLLM_RAGGED_DEEPSEEK_PREFILL: '0'
+    VLLM_USE_NCCL_SYMM_MEM: '1'
+    UCX_IB_ROCE_REACHABILITY_MODE: local_subnet
+    VLLM_NIXL_SIDE_CHANNEL_PORT: '5600'
+    VLLM_NIXL_ABORT_REQUEST_TIMEOUT: '300'
+    VLLM_MOE_DP_CHUNK_SIZE: '384'
+    VLLM_SHARED_EXPERTS_STREAM_TOKEN_THRESHOLD: '8192'
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: cuda_ipc,cuda_copy,rc
+  vllm_config:
+    prefill:
+      tensor-parallel-size: 1
+      pipeline-parallel-size: 1
+      enable-expert-parallel: true
+      data-parallel-size: 2
+      data-parallel-rpc-port: 13345
+      data-parallel-hybrid-lb: true
+      max-model-len: 9472
+      max-num-seqs: 16
+      enforce-eager: true
+      gpu-memory-utilization: 0.9
+      max-num-batched-tokens: 16384
+      no-enable-chunked-prefill: true
+      kv-cache-dtype: fp8
+      async-scheduling: true
+      no-enable-prefix-caching: true
+      trust-remote-code: true
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      block-size: 128
+      language-model-only: true
+      stream-interval: 32
+      max-cudagraph-capture-size: 2048
+    decode:
+      tensor-parallel-size: 4
+      pipeline-parallel-size: 1
+      enable-expert-parallel: false
+      max-model-len: 9472
+      max-num-seqs: 256
+      gpu-memory-utilization: 0.9
+      max-num-batched-tokens: 16384
+      max-cudagraph-capture-size: 2048
+      compilation-config: '{"cudagraph_mode":"FULL_DECODE_ONLY","custom_ops":["+rms_norm"],"pass_config":{}}'
+      kv-cache-dtype: fp8
+      all2all-backend: deepep_low_latency
+      async-scheduling: true
+      stream-interval: 32
+      enable-dbo: true
+      dbo-decode-token-threshold: 32
+      no-enable-prefix-caching: true
+      trust-remote-code: true
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      block-size: 128
+      language-model-only: true
+benchmark:
+  type: sa-bench
+  isl: 8192
+  osl: 1024
+  concurrencies: '512'
+  req_rate: inf
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  args:
+    dyn-chat-processor: vllm
+    reasoning-parser: minimax_m3
+dynamo:
+  install: false
+  version: 1.2.1
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/4p2d-dep2-tp4-c1024-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/4p2d-dep2-tp4-c1024-8k1k.yaml
new file mode 100644
index 000000000..8b2708447
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4/8k1k/4p2d-dep2-tp4-c1024-8k1k.yaml
@@ -0,0 +1,127 @@
+name: minimax-m3-vllm-disagg-b200-4p2d-fp4-dep2-tp4-c1024-8k1k
+model:
+  path: nvidia/MiniMax-M3-NVFP4
+  container: vllm/vllm-openai:cu129-nightly-8e981630c9336233ca9de91452f68918bddbc4e2
+  precision: fp4
+resources:
+  gpu_type: b200
+  prefill_nodes: 2
+  prefill_workers: 4
+  gpus_per_prefill: 2
+  decode_nodes: 2
+  decode_workers: 2
+  spread_workers: true
+  gpus_per_decode: 4
+  gpus_per_node: 8
+backend:
+  type: vllm
+  connector: null
+  prefill_environment:
+    VLLM_USE_DEEP_GEMM: '1'
+    VLLM_SKIP_P2P_CHECK: '1'
+    VLLM_RANDOMIZE_DP_DUMMY_INPUTS: '1'
+    NVIDIA_GDRCOPY: '1'
+    PYTHONUNBUFFERED: '1'
+    VLLM_LOG_STATS_INTERVAL: '1'
+    NVSHMEM_IB_ENABLE_IBGDA: '1'
+    NCCL_CUMEM_ENABLE: '1'
+    NCCL_MNNVL_ENABLE: '1'
+    NCCL_NVLS_ENABLE: '1'
+    NCCL_TIMEOUT: '1800'
+    TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC: '1800'
+    VLLM_USE_FLASHINFER_MOE_FP4: '1'
+    VLLM_USE_TRTLLM_RAGGED_DEEPSEEK_PREFILL: '0'
+    VLLM_USE_NCCL_SYMM_MEM: '1'
+    UCX_IB_ROCE_REACHABILITY_MODE: local_subnet
+    VLLM_NIXL_SIDE_CHANNEL_PORT: '5600'
+    VLLM_NIXL_ABORT_REQUEST_TIMEOUT: '300'
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: cuda_ipc,cuda_copy,rc
+  decode_environment:
+    VLLM_USE_DEEP_GEMM: '1'
+    VLLM_SKIP_P2P_CHECK: '1'
+    VLLM_RANDOMIZE_DP_DUMMY_INPUTS: '1'
+    NVIDIA_GDRCOPY: '1'
+    PYTHONUNBUFFERED: '1'
+    VLLM_LOG_STATS_INTERVAL: '1'
+    NVSHMEM_IB_ENABLE_IBGDA: '1'
+    NCCL_CUMEM_ENABLE: '1'
+    NCCL_MNNVL_ENABLE: '1'
+    NCCL_NVLS_ENABLE: '1'
+    NCCL_TIMEOUT: '1800'
+    TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC: '1800'
+    VLLM_USE_FLASHINFER_MOE_FP4: '1'
+    VLLM_USE_TRTLLM_RAGGED_DEEPSEEK_PREFILL: '0'
+    VLLM_USE_NCCL_SYMM_MEM: '1'
+    UCX_IB_ROCE_REACHABILITY_MODE: local_subnet
+    VLLM_NIXL_SIDE_CHANNEL_PORT: '5600'
+    VLLM_NIXL_ABORT_REQUEST_TIMEOUT: '300'
+    VLLM_MOE_DP_CHUNK_SIZE: '384'
+    VLLM_SHARED_EXPERTS_STREAM_TOKEN_THRESHOLD: '8192'
+    VLLM_FLOAT32_MATMUL_PRECISION: high
+    UCX_TLS: cuda_ipc,cuda_copy,rc
+  vllm_config:
+    prefill:
+      tensor-parallel-size: 1
+      pipeline-parallel-size: 1
+      enable-expert-parallel: true
+      data-parallel-size: 2
+      data-parallel-rpc-port: 13345
+      data-parallel-hybrid-lb: true
+      max-model-len: 9472
+      max-num-seqs: 16
+      enforce-eager: true
+      gpu-memory-utilization: 0.9
+      max-num-batched-tokens: 16384
+      no-enable-chunked-prefill: true
+      kv-cache-dtype: fp8
+      async-scheduling: true
+      no-enable-prefix-caching: true
+      trust-remote-code: true
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      block-size: 128
+      language-model-only: true
+      stream-interval: 32
+      max-cudagraph-capture-size: 2048
+    decode:
+      tensor-parallel-size: 4
+      pipeline-parallel-size: 1
+      enable-expert-parallel: false
+      max-model-len: 9472
+      max-num-seqs: 512
+      gpu-memory-utilization: 0.9
+      max-num-batched-tokens: 16384
+      max-cudagraph-capture-size: 2048
+      compilation-config: '{"cudagraph_mode":"FULL_DECODE_ONLY","custom_ops":["+rms_norm"],"pass_config":{}}'
+      kv-cache-dtype: fp8
+      all2all-backend: deepep_low_latency
+      async-scheduling: true
+      stream-interval: 32
+      enable-dbo: true
+      dbo-decode-token-threshold: 32
+      no-enable-prefix-caching: true
+      trust-remote-code: true
+      served-model-name: nvidia/MiniMax-M3-NVFP4
+      no-enable-flashinfer-autotune: true
+      kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
+      attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
+      block-size: 128
+      language-model-only: true
+benchmark:
+  type: sa-bench
+  isl: 8192
+  osl: 1024
+  concurrencies: '1024'
+  req_rate: inf
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  args:
+    dyn-chat-processor: vllm
+    reasoning-parser: minimax_m3
+dynamo:
+  install: false
+  version: 1.2.1
diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 33e9118b7..5ed47cfb8 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -13211,6 +13211,101 @@ qwen3.5-fp8-h100-sglang-agentic:
       - { tp: 8, ep: 8, kv-offloading: none,    conc-list: [1, 2, 4, 8, 12, 14, 16] }
       - { tp: 8, ep: 8, kv-offloading: dram, kv-offload-backend: { name: hicache }, conc-list: [12, 14, 16, 20, 24, 28, 32, 42] }
 
+minimaxm3-fp4-b200-dynamo-vllm:
+  image: vllm/vllm-openai:cu129-nightly-8e981630c9336233ca9de91452f68918bddbc4e2
+  model: nvidia/MiniMax-M3-NVFP4
+  model-prefix: minimaxm3
+  runner: b200-multinode
+  precision: fp4
+  framework: dynamo-vllm
+  router: { name: dynamo-router, version: "1.2.1" }
+  kv-p2p-transfer: nixl
+  multinode: true
+  disagg: true
+  scenarios:
+    fixed-seq-len:
+    - isl: 8192
+      osl: 1024
+      search-space:
+      - conc-list: [1, 4, 8, 16]
+        prefill:
+          num-worker: 1
+          tp: 2
+          ep: 2
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/vllm/minimax-m3/b200-fp4/8k1k/1p1d-dep2-tp4-c1-c16-8k1k.yaml"
+        decode:
+          num-worker: 1
+          tp: 4
+          ep: 1
+          dp-attn: false
+      - conc-list: [64]
+        prefill:
+          num-worker: 1
+          tp: 2
+          ep: 2
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/vllm/minimax-m3/b200-fp4/8k1k/1p2d-dep2-tp4-c64-8k1k.yaml"
+        decode:
+          num-worker: 2
+          tp: 4
+          ep: 1
+          dp-attn: false
+      - conc-list: [128]
+        prefill:
+          num-worker: 2
+          tp: 2
+          ep: 2
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/vllm/minimax-m3/b200-fp4/8k1k/2p2d-dep2-tp4-c128-8k1k.yaml"
+        decode:
+          num-worker: 2
+          tp: 4
+          ep: 1
+          dp-attn: false
+      - conc-list: [256]
+        prefill:
+          num-worker: 3
+          tp: 2
+          ep: 2
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/vllm/minimax-m3/b200-fp4/8k1k/3p2d-dep2-tp4-c256-8k1k.yaml"
+        decode:
+          num-worker: 2
+          tp: 4
+          ep: 1
+          dp-attn: false
+      - conc-list: [512]
+        prefill:
+          num-worker: 3
+          tp: 2
+          ep: 2
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/vllm/minimax-m3/b200-fp4/8k1k/3p2d-dep2-tp4-c512-8k1k.yaml"
+        decode:
+          num-worker: 2
+          tp: 4
+          ep: 1
+          dp-attn: false
+      - conc-list: [1024]
+        prefill:
+          num-worker: 4
+          tp: 2
+          ep: 2
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/vllm/minimax-m3/b200-fp4/8k1k/4p2d-dep2-tp4-c1024-8k1k.yaml"
+        decode:
+          num-worker: 2
+          tp: 4
+          ep: 1
+          dp-attn: false
+
 # MiniMax-M3 NVFP4 disagg sweep on the same B300 topology matrix as the MXFP8
 # baseline above. The image includes vLLM PR #46380, so no runtime patch is
 # needed.
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 04991f247..2184310f1 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4875,3 +4875,12 @@
     - "Add SGLANG_MAMBA_SSM_DTYPE=bfloat16 in both non-MTP and MTP benchmark scripts"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2201  
 
+- config-keys:
+    - minimaxm3-fp4-b200-dynamo-vllm
+  description:
+    - "Add MiniMax-M3 NVFP4 B200 Dynamo-vLLM disaggregated benchmarks at 8k/1k."
+    - "Use validated configurations from concurrency 1 through 1024, including the corrected spread-decode c64 point."
+    - "Image: vllm/vllm-openai:cu129-nightly-8e981630c9336233ca9de91452f68918bddbc4e2."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2230
+
+
diff --git a/runners/launch_b200-dgxc.sh b/runners/launch_b200-dgxc.sh
index 58051e640..23d7a1aa3 100644
--- a/runners/launch_b200-dgxc.sh
+++ b/runners/launch_b200-dgxc.sh
@@ -69,9 +69,8 @@ elif [[ $MODEL_PREFIX == "minimaxm3" && $PRECISION == "fp8" ]]; then
     export MODEL_PATH="/lustre/fsw/gharunners/models/MiniMax-M3-MXFP8"
     export SRT_SLURM_MODEL_PREFIX="minimax-m3-mxfp8"
 elif [[ $MODEL_PREFIX == "minimaxm3" && $PRECISION == "fp4" ]]; then
-    # NVFP4 checkpoint, pre-staged on the b200-dgxc scratch tree.
     export MODEL_PATH="/scratch/fsw/models/MiniMax-M3-NVFP4"
-    export SRT_SLURM_MODEL_PREFIX="minimax-m3-nvfp4"
+    export SRT_SLURM_MODEL_PREFIX="nvidia/MiniMax-M3-NVFP4"
 else
     echo "Unsupported model prefix/precision: $MODEL_PREFIX/$PRECISION"
     echo "Available models under /lustre/fsw/models:"
@@ -113,6 +112,13 @@ if [[ "$IS_MULTINODE" == "true" ]]; then
         git checkout aflowers/vllm-gb200-v0.20.0
         mkdir -p recipes/vllm/deepseek-v4
         cp -rT "$GITHUB_WORKSPACE/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4" recipes/vllm/deepseek-v4
+    elif [[ $FRAMEWORK == "dynamo-vllm" && $MODEL_PREFIX == "minimaxm3" && $PRECISION == "fp4" ]]; then
+        git clone https://github.com/NVIDIA/srt-slurm.git "$SRT_REPO_DIR"
+        cd "$SRT_REPO_DIR" || exit 1
+        mkdir -p recipes/vllm/minimax-m3/b200-fp4
+        cp -rT \
+            "$GITHUB_WORKSPACE/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b200-fp4" \
+            recipes/vllm/minimax-m3/b200-fp4
     elif [[ $FRAMEWORK == "dynamo-sglang" && $MODEL_PREFIX == "glm5" && $PRECISION == "fp8" ]]; then
         git clone https://github.com/NVIDIA/srt-slurm.git "$SRT_REPO_DIR"
         cd "$SRT_REPO_DIR" || exit 1