[NV] minimax-m3-gb300-dynamo: nightly image + 2xDEP8 decode to 1xDEP16 / [NV] minimax-m3-gb300-dynamo：nightly 镜像 + 2×DEP8 解码合并为 1×DEP16 (#2340)

xinli-sw · Ankur-singh · web-flow · commit 4e8bd8e14cc2 · 2026-07-29T14:28:05.000-07:00
* [NV] minimax-m3-gb300-dynamo: vLLM nightly + dynamo bump; collapse 2xDEP8 decode to 1xDEP16

minimaxm3-fp8-gb300-dynamo-vllm:
- image -&gt; vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9
- dynamo -&gt; 1.3.0.dev20260710 (recipe files)
- drop minimax-m3-gb300-vllm-fixes.sh setup patch + launcher wiring (shipped in the nightly image)
- the one 2xDEP8 decode (3p2d, conc 512) -&gt; 1xDEP16 (decode_workers 2-&gt;1,
  gpus_per_decode 8-&gt;16, data-parallel-size 8-&gt;16); recipe renamed
  3p2d-dep2-dep8 -&gt; 3p1d-dep2-dep16

* [NV] minimax-m3-gb300-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-gb300-vllm-fixes.sh b/benchmarks/multi_node/srt-slurm-recipes/configs/minimax-m3-gb300-vllm-fixes.sh
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/1p1d-dep2-dep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/1p1d-dep2-dep8-8k1k.yaml
@@ -6,13 +6,13 @@ name: "minimax-m3-vllm-disagg-gb300-1p1d-dep2-dep8-fp8-8k1k"
 
 model:
   path: "minimax-m3-mxfp8"
-  container: "vllm/vllm-openai:minimax-m3-perf-arm64-13.0.1-7a67223"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 health_check:
   max_attempts: 720
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/1p1d-dep2-tep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/1p1d-dep2-tep8-8k1k.yaml
@@ -6,13 +6,13 @@ name: "minimax-m3-vllm-disagg-gb300-1p1d-dep2-tep8-fp8-8k1k"
 
 model:
   path: "minimax-m3-mxfp8"
-  container: "vllm/vllm-openai:minimax-m3-perf-arm64-13.0.1-7a67223"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 health_check:
   max_attempts: 720
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/1p2d-dep2-tep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/1p2d-dep2-tep8-8k1k.yaml
@@ -6,13 +6,13 @@ name: "minimax-m3-vllm-disagg-gb300-1p2d-dep2-tep8-fp8-8k1k"
 
 model:
   path: "minimax-m3-mxfp8"
-  container: "vllm/vllm-openai:minimax-m3-perf-arm64-13.0.1-7a67223"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 health_check:
   max_attempts: 720
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/2p1d-dep2-dep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/2p1d-dep2-dep8-8k1k.yaml
@@ -6,13 +6,13 @@ name: "minimax-m3-vllm-disagg-gb300-2p1d-dep2-dep8-fp8-8k1k"
 
 model:
   path: "minimax-m3-mxfp8"
-  container: "vllm/vllm-openai:minimax-m3-perf-arm64-13.0.1-7a67223"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 health_check:
   max_attempts: 720
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/2p2d-dep2-tep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/2p2d-dep2-tep8-8k1k.yaml
@@ -6,13 +6,13 @@ name: "minimax-m3-vllm-disagg-gb300-2p2d-dep2-tep8-fp8-8k1k"
 
 model:
   path: "minimax-m3-mxfp8"
-  container: "vllm/vllm-openai:minimax-m3-perf-arm64-13.0.1-7a67223"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 health_check:
   max_attempts: 720
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/2p4d-dep2-tep4-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/2p4d-dep2-tep4-8k1k.yaml
@@ -6,13 +6,13 @@ name: "minimax-m3-vllm-disagg-gb300-2p4d-dep2-tep4-fp8-8k1k"
 
 model:
   path: "minimax-m3-mxfp8"
-  container: "vllm/vllm-openai:minimax-m3-perf-arm64-13.0.1-7a67223"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 health_check:
   max_attempts: 720
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/3p1d-dep2-dep16-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/3p1d-dep2-dep16-8k1k.yaml
@@ -1,18 +1,18 @@
-name: "minimax-m3-vllm-disagg-gb300-3p2d-dep2-dep8-fp8-8k1k"
+name: "minimax-m3-vllm-disagg-gb300-3p1d-dep2-dep16-fp8-8k1k"
 
 # 3P DEP2 prefill (TP1 DP2 EP, 2 GPU/worker) + 2D DEP8 decode (TP1 DP8 EP, 8 GPU/worker = 2 nodes each).
 # GB300 has 4 GPUs/node. Adapted from NV B300 PR #1863.
 # Nodes: 2 prefill + 4 decode (+ head/infra).
 
 model:
   path: "minimax-m3-mxfp8"
-  container: "vllm/vllm-openai:minimax-m3-perf-arm64-13.0.1-7a67223"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 health_check:
   max_attempts: 720
@@ -31,9 +31,9 @@ resources:
   prefill_nodes: 2
   decode_nodes: 4
   prefill_workers: 3
-  decode_workers: 2
+  decode_workers: 1
   gpus_per_prefill: 2
-  gpus_per_decode: 8
+  gpus_per_decode: 16
 
 frontend:
   type: dynamo
@@ -84,7 +84,7 @@ backend:
       kv-transfer-config: '{"kv_connector": "NixlConnector", "kv_role": "kv_both"}'
       attention-config: '{"backend": "FLASHINFER", "use_trtllm_attention": true, "indexer_kv_dtype": "fp8"}'
       tensor-parallel-size: 1
-      data-parallel-size: 8
+      data-parallel-size: 16
       data-parallel-rpc-port: 13345
       enable-expert-parallel: true
       trust-remote-code: true
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/3p1d-dep2-dep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/3p1d-dep2-dep8-8k1k.yaml
@@ -6,13 +6,13 @@ name: "minimax-m3-vllm-disagg-gb300-3p1d-dep2-dep8-fp8-8k1k"
 
 model:
   path: "minimax-m3-mxfp8"
-  container: "vllm/vllm-openai:minimax-m3-perf-arm64-13.0.1-7a67223"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 health_check:
   max_attempts: 720
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/6p1d-dep2-dep8-8k1k.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8/8k1k/6p1d-dep2-dep8-8k1k.yaml
@@ -6,13 +6,13 @@ name: "minimax-m3-vllm-disagg-gb300-6p1d-dep2-dep8-fp8-8k1k"
 
 model:
   path: "minimax-m3-mxfp8"
-  container: "vllm/vllm-openai:minimax-m3-perf-arm64-13.0.1-7a67223"
+  container: "vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9"
   precision: "fp8"
 
 
 dynamo:
   install: true
-  version: 1.3.0.dev20260614
+  version: 1.3.0.dev20260710
 
 health_check:
   max_attempts: 720
diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
@@ -7289,7 +7289,7 @@ minimaxm3-fp4-b300-dynamo-vllm-mtp-legacy-dep4:
 # All prefill DEP2 (TP1 DP2 EP, 2 GPU/worker). Decode: DEP4, TEP8, DEP8, TEP4.
 # 4 GPU/node (GB300 NVL72). kv-cache-dtype=fp8. srun_options mem=0 required.
 minimaxm3-fp8-gb300-dynamo-vllm:
-  image: vllm/vllm-openai:minimax-m3-perf-arm64-13.0.1-7a67223
+  image: vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9
   model: MiniMaxAI/MiniMax-M3-MXFP8
   model-prefix: minimaxm3
   runner: gb300-nv
@@ -7409,19 +7409,19 @@ minimaxm3-fp8-gb300-dynamo-vllm:
           ep: 8
           dp-attn: true
 
-      # 3p2d DEP2+DEP8, 6n: conc 512
+      # 3p1d DEP2+DEP16, 6n: conc 512
       - conc-list: [512]
         prefill:
           num-worker: 3
           tp: 2
           ep: 2
           dp-attn: true
           additional-settings:
-          - "CONFIG_FILE=recipes/vllm/minimax-m3-gb300-fp8/8k1k/3p2d-dep2-dep8-8k1k.yaml"
+          - "CONFIG_FILE=recipes/vllm/minimax-m3-gb300-fp8/8k1k/3p1d-dep2-dep16-8k1k.yaml"
         decode:
-          num-worker: 2
-          tp: 8
-          ep: 8
+          num-worker: 1
+          tp: 16
+          ep: 16
           dp-attn: true
 
       # 6p1d DEP2+DEP8, 5n: conc 2048
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
@@ -5223,3 +5223,10 @@
     - "Bump image to vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9 and dynamo to 1.3.0.dev20260710; drop the minimax-m3-gb200-vllm-fixes.sh setup patch (shipped in the nightly image)"
     - "Collapse every 2xDEP8 decode into a single DEP16 worker (decode_workers 2->1, gpus_per_decode 8->16, data-parallel-size 8->16); recipes renamed Xp2d-dep4-dep8 -> Xp1d-dep4-dep16 (1p2d/2p2d/3p2d/5p2d)"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2339
+
+- config-keys:
+    - minimaxm3-fp8-gb300-dynamo-vllm
+  description:
+    - "Bump image to vllm/vllm-openai:nightly-4080263bb2c5d10deac17aaeb88e0823bc35bca9 and dynamo to 1.3.0.dev20260710; drop the minimax-m3-gb300-vllm-fixes.sh setup patch (shipped in the nightly image)"
+    - "Collapse the 2xDEP8 decode into a single DEP16 worker (decode_workers 2->1, gpus_per_decode 8->16, data-parallel-size 8->16); recipe renamed 3p2d-dep2-dep8 -> 3p1d-dep2-dep16 (conc 512). The remaining decodes are 1xDEP8 or TEP and are unchanged."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2340
diff --git a/runners/launch_gb300-nv.sh b/runners/launch_gb300-nv.sh
@@ -212,10 +212,6 @@ elif [[ $FRAMEWORK == "dynamo-vllm" && $MODEL_PREFIX == "minimaxm3" ]]; then
     git checkout sa-submission-q2-2026
     mkdir -p recipes/vllm/minimax-m3-gb300-fp8
     cp -rT "$GITHUB_WORKSPACE/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3-gb300-fp8" recipes/vllm/minimax-m3-gb300-fp8
-    SRTCTL_SETUP_SCRIPT="minimax-m3-gb300-vllm-fixes.sh"
-    cp \
-        "$GITHUB_WORKSPACE/benchmarks/multi_node/srt-slurm-recipes/configs/$SRTCTL_SETUP_SCRIPT" \
-        "configs/$SRTCTL_SETUP_SCRIPT"
 elif [[ $FRAMEWORK == "dynamo-vllm" && $MODEL_PREFIX == "kimik2.5" && $PRECISION == "fp4" ]]; then
     git clone https://github.com/NVIDIA/srt-slurm.git "$SRT_REPO_DIR"
     cd "$SRT_REPO_DIR"
