[NV] minimax-m3-B300-dynamo: use vLLM nightly image / [NV] minimax-m3-B300-dynamo：使用 vLLM nightly 镜像 (#2338)

xinli-sw · Ankur-singh · web-flow · commit 4ea94c9698d5 · 2026-07-29T13:57:47.000-07:00
* [NV] minimax-m3-b300-dynamo: vLLM nightly + dynamo bump; swap conc-4096 tep4 arm for 3p2d-dep2-dep8

minimaxm3-fp8-b300-dynamo-vllm:
- image -&gt; vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9
- dynamo -&gt; 1.3.0.dev20260710 (recipe files)
- drop minimax-m3-vllm-fixes.sh setup patch + launcher wiring (shipped in the nightly image)
- conc 4096: drop 4p2d-dep2-tep4 arm; add 3p2d-dep2-dep8 for conc [1024, 2048]
  (prefill 3xDEP2, decode 2xDEP8)

* [NV] minimax-m3-b300-dynamo: add perf-changelog pr-link

---------

Co-authored-by: Ankur-singh &lt;ankusingh@nvidia.com&gt;
diff --git a/benchmarks/multi_node/srt-slurm-recipes/configs/minimax-m3-vllm-fixes.sh b/benchmarks/multi_node/srt-slurm-recipes/configs/minimax-m3-vllm-fixes.sh
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/1p1d-dep2-tp4-marlin-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/1p1d-dep2-tp4-marlin-8k1k.yaml
@@ -2,7 +2,7 @@ name: "minimax-m3-vllm-disagg-b300-1p1d-fp8-dep2-tp4-marlin-8k1k"
 
 model:
   path: "MiniMaxAI/MiniMax-M3-MXFP8"
-  container: "vllm/vllm-openai:minimax-m3-0618-x86_64-cu130"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 resources:
@@ -17,7 +17,7 @@ resources:
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 frontend:
   type: dynamo
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/1p2d-dep2-tep4-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/1p2d-dep2-tep4-8k1k.yaml
@@ -2,7 +2,7 @@ name: "minimax-m3-vllm-disagg-b300-1p2d-fp8-dep2-tep4-8k1k"
 
 model:
   path: "MiniMaxAI/MiniMax-M3-MXFP8"
-  container: "vllm/vllm-openai:minimax-m3-0618-x86_64-cu130"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 resources:
@@ -17,7 +17,7 @@ resources:
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 frontend:
   type: dynamo
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/1p4d-dep2-tep4-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/1p4d-dep2-tep4-8k1k.yaml
@@ -2,7 +2,7 @@ name: "minimax-m3-vllm-disagg-b300-1p4d-fp8-dep2-tep4-8k1k"
 
 model:
   path: "MiniMaxAI/MiniMax-M3-MXFP8"
-  container: "vllm/vllm-openai:minimax-m3-0618-x86_64-cu130"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 resources:
@@ -17,7 +17,7 @@ resources:
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 frontend:
   type: dynamo
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/1p4d-dep2-tep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/1p4d-dep2-tep8-8k1k.yaml
@@ -2,7 +2,7 @@ name: "minimax-m3-vllm-disagg-b300-1p4d-fp8-dep2-tep8-8k1k"
 
 model:
   path: "MiniMaxAI/MiniMax-M3-MXFP8"
-  container: "vllm/vllm-openai:minimax-m3-0618-x86_64-cu130"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 resources:
@@ -17,7 +17,7 @@ resources:
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 frontend:
   type: dynamo
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/2p2d-dep2-dep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/2p2d-dep2-dep8-8k1k.yaml
@@ -2,7 +2,7 @@ name: "minimax-m3-vllm-disagg-b300-2p2d-fp8-dep2-dep8-8k1k"
 
 model:
   path: "MiniMaxAI/MiniMax-M3-MXFP8"
-  container: "vllm/vllm-openai:minimax-m3-0618-x86_64-cu130"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 resources:
@@ -17,7 +17,7 @@ resources:
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 frontend:
   type: dynamo
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/2p2d-dep2-tep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/2p2d-dep2-tep8-8k1k.yaml
@@ -2,7 +2,7 @@ name: "minimax-m3-vllm-disagg-b300-2p2d-fp8-dep2-tep8-8k1k"
 
 model:
   path: "MiniMaxAI/MiniMax-M3-MXFP8"
-  container: "vllm/vllm-openai:minimax-m3-0618-x86_64-cu130"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 resources:
@@ -17,7 +17,7 @@ resources:
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 frontend:
   type: dynamo
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/3p2d-dep2-dep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/3p2d-dep2-dep8-8k1k.yaml
@@ -1,23 +1,23 @@
-name: "minimax-m3-vllm-disagg-b300-4p2d-fp8-dep2-tep4-8k1k"
+name: "minimax-m3-vllm-disagg-b300-3p2d-fp8-dep2-dep8-8k1k"
 
 model:
   path: "MiniMaxAI/MiniMax-M3-MXFP8"
-  container: "vllm/vllm-openai:minimax-m3-0618-x86_64-cu130"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 resources:
   gpu_type: "b300"
   gpus_per_node: 8
   prefill_nodes: 1
-  decode_nodes: 1
-  prefill_workers: 4
+  decode_nodes: 2
+  prefill_workers: 3
   decode_workers: 2
   gpus_per_prefill: 2
-  gpus_per_decode: 4
+  gpus_per_decode: 8
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 frontend:
   type: dynamo
@@ -55,7 +55,9 @@ backend:
       max-num-batched-tokens: 16384
 
     decode:
-      tensor-parallel-size: 4
+      tensor-parallel-size: 1
+      data-parallel-size: 8
+      data-parallel-rpc-port: 13345
       enable-expert-parallel: true
       trust-remote-code: true
       no-enable-prefix-caching: true
@@ -67,7 +69,7 @@ backend:
       max-model-len: 9472
       language-model-only: true
       stream-interval: 32
-      max-num-seqs: 1024
+      max-num-seqs: 1024  # Per DP rank: 2 workers x DP8 = 16 ranks.
       max-num-batched-tokens: 16384
       max-cudagraph-capture-size: 4096
 
@@ -79,5 +81,5 @@ benchmark:
   type: "sa-bench"
   isl: 8192
   osl: 1024
-  concurrencies: "4096"
+  concurrencies: "1024x2048"
   req_rate: "inf"
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/4p2d-dep2-dep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/b300-fp8/8k1k/4p2d-dep2-dep8-8k1k.yaml
@@ -2,7 +2,7 @@ name: "minimax-m3-vllm-disagg-b300-4p2d-fp8-dep2-dep8-8k1k"
 
 model:
   path: "MiniMaxAI/MiniMax-M3-MXFP8"
-  container: "vllm/vllm-openai:minimax-m3-0618-x86_64-cu130"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 resources:
@@ -17,7 +17,7 @@ resources:
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 frontend:
   type: dynamo
diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
@@ -6885,7 +6885,7 @@ minimaxm3-fp4-b200-dynamo-vllm:
 # baseline above. The image includes vLLM PR #46380, so no runtime patch is
 # needed.
 minimaxm3-fp8-b300-dynamo-vllm:
-  image: vllm/vllm-openai:minimax-m3-0618-x86_64-cu130
+  image: vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9
   model: MiniMaxAI/MiniMax-M3-MXFP8
   model-prefix: minimaxm3
   runner: b300
@@ -6952,19 +6952,19 @@ minimaxm3-fp8-b300-dynamo-vllm:
           tp: 4
           ep: 1
           dp-attn: false
-      - conc-list: [4096]
+      - conc-list: [1024, 2048]
         prefill:
-          num-worker: 4
+          num-worker: 3
           tp: 2
           ep: 2
           dp-attn: true
           additional-settings:
-          - "CONFIG_FILE=recipes/vllm/minimax-m3/b300-fp8/8k1k/4p2d-dep2-tep4-8k1k.yaml"
+          - "CONFIG_FILE=recipes/vllm/minimax-m3/b300-fp8/8k1k/3p2d-dep2-dep8-8k1k.yaml"
         decode:
           num-worker: 2
-          tp: 4
-          ep: 4
-          dp-attn: false
+          tp: 8
+          ep: 8
+          dp-attn: true
       - conc-list: [16, 32, 64, 128]
         prefill:
           num-worker: 1
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
@@ -5209,3 +5209,10 @@
     - "Use configurations from concurrency 1 through 1024 with spread worker placement for CI transport validation."
     - "Image: vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9; Dynamo: 1.3.0.dev20260710."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2230
+
+- config-keys:
+    - minimaxm3-fp8-b300-dynamo-vllm
+  description:
+    - "Bump image to vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9 and dynamo to 1.3.0.dev20260710; drop the minimax-m3-vllm-fixes.sh setup patch (shipped in the nightly image)"
+    - "conc 4096: drop the 4p2d-dep2-tep4 arm; add a 3p2d-dep2-dep8 arm for conc [1024, 2048] (prefill 3xDEP2, decode 2xDEP8)"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2338
diff --git a/runners/launch_b300-nv.sh b/runners/launch_b300-nv.sh
@@ -94,9 +94,6 @@ elif [[ $FRAMEWORK == "dynamo-vllm" && $MODEL_PREFIX == "minimaxm3" && ( $PRECIS
     git checkout sa-submission-q2-2026
     mkdir -p recipes/vllm/minimax-m3
     cp -rT "$GITHUB_WORKSPACE/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3" recipes/vllm/minimax-m3
-    if [[ $PRECISION == "fp8" ]]; then
-        SRTCTL_SETUP_SCRIPT="minimax-m3-vllm-fixes.sh"
-    fi
     # NVIDIA/srt-slurm#38
     git show 22d46ba9971615016d2339c9ffbc7b4597accfad --format= -- src/srtctl/core/ip_utils/get_node_ip.sh | git apply - || exit 1
     if [[ -n "$SRTCTL_SETUP_SCRIPT" ]]; then
