Run Kimi K2.6 NVFP4 Dynamo vLLM on b200-new / 在 b200-new 上运行 Kimi K2.6 NVFP4 Dynamo vLLM

configs/nvidia-master.yaml

@@ -4816,7 +4816,7 @@ kimik2.6-fp4-b200-dynamo-vllm:
   image: vllm/vllm-openai:v0.25.1
   model: nvidia/Kimi-K2.6-NVFP4
   model-prefix: kimik2.6
-  runner: b200-multinode
+  runner: b200-new
   precision: fp4
   framework: dynamo-vllm
   router: { name: dynamo-router, version: "1.3.0.dev20260721" }
@@ -4880,19 +4880,6 @@ kimik2.6-fp4-b200-dynamo-vllm:
           tp: 4
           ep: 1
           dp-attn: false
-      - conc-list: [1024]
-        prefill:
-          num-worker: 1
-          tp: 1
-          ep: 4
-          dp-attn: true
-          additional-settings:
-          - "CONFIG_FILE=recipes/vllm/kimi-k2.6/b200-fp4/8k1k/disagg-b200-1p1d-dep4-dep8-c1024.yaml"
-        decode:
-          num-worker: 1
-          tp: 1
-          ep: 8
-          dp-attn: true
       - conc-list: [2048]
         prefill:
           num-worker: 1

configs/runners.yaml

@@ -80,6 +80,16 @@ labels:
     - b200-dgxc-slurm_7
     - b200-dgxc-slurm_8
     - b200-dgxc-slurm_9
+  b200-new:
+    - b200-nscale-slurm_0
+    - b200-nscale-slurm_1
+    - b200-nscale-slurm_2
+    - b200-nscale-slurm_3
+    - b200-nscale-slurm_4
+    - b200-nscale-slurm_5
+    - b200-nscale-slurm_6
+    - b200-nscale-slurm_7
+    - b200-nscale-slurm_8
   mi300x:
     - mi300x-amds_00
     - mi300x-amds_01

perf-changelog.yaml

@@ -5475,3 +5475,11 @@
     - "9 MTP configs: 1P1D DEP2+1D TEP16 (conc 48), 1P4D DEP2+4D TP16 (conc 4), 1P7D DEP2+7D TEP8 (conc 42), 2P15D DEP2+15D TP4 (conc 90), 3P4D DEP2+4D TEP8 (conc 192), 3P7D DEP2+7D TEP8 (conc 168), 4P1D DEP2+1D DEP16 (conc 384), 6P5D DEP2+5D TEP8 (conc 480), 9P1D DEP2+1D DEP16 (conc 1536)."
     - "Runner: launch_gb300-nv.sh updated to clone NVIDIA/srt-slurm@v1.0.29 and overlay local recipes from benchmarks/multi_node/srt-slurm-recipes/trtllm/qwen3.5/gb300-fp4/disagg/ for the dynamo-trt+qwen3.5+fp4 path; --no-preflight added for model on compute-node /scratch."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2218
+
+- config-keys:
+    - kimik2.6-fp4-b200-dynamo-vllm
+  description:
+    - "Run the Kimi K2.6 NVFP4 B200 Dynamo vLLM disaggregated configuration on the b200-new runner."
+    - "Remove the 1P/1D DEP4-to-DEP8 concurrency-1024 configuration."
+    - "Image: vllm/vllm-openai:v0.25.1"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2438

runners/launch_b200-dgxc.sh

@@ -1,8 +1,8 @@
 #!/usr/bin/bash
 
 # System-specific configuration for B200 DGXC Slurm cluster
-SLURM_PARTITION="gpu-2"
-SLURM_ACCOUNT="benchmark"
+SLURM_PARTITION="${SLURM_PARTITION:-gpu-2}"
+SLURM_ACCOUNT="${SLURM_ACCOUNT:-benchmark}"
 
 set -x
 
@@ -53,7 +53,7 @@ elif [[ $MODEL_PREFIX == "kimik2.5" && $PRECISION == "fp4" ]]; then
     export MODEL_PATH="/lustre/fsw/models/Kimi-K2.5-NVFP4"
     export SRT_SLURM_MODEL_PREFIX="kimik2.5-fp4"
 elif [[ $MODEL_PREFIX == "kimik2.6" && $PRECISION == "fp4" ]]; then
-    export MODEL_PATH="/lustre/fsw/models/Kimi-K2.6-NVFP4"
+    export MODEL_PATH="${MODEL_PATH:-/lustre/fsw/models/Kimi-K2.6-NVFP4}"
     export SRT_SLURM_MODEL_PREFIX="kimi-k2.6-nvfp4"
 elif [[ $MODEL_PREFIX == "minimaxm2.5" && $PRECISION == "fp8" ]]; then
     export MODEL_PATH="/lustre/fsw/models/MiniMax-M2.5"
@@ -213,7 +213,7 @@ if [[ "$IS_MULTINODE" == "true" ]]; then
         local lock_file="${lock_dir}/${image_key}.lock"
 
         (
-            flock -w 600 9 || { echo "Failed to acquire lock for $squash_file" >&2; exit 1; }
+            flock -w "${B200_SQUASH_LOCK_TIMEOUT:-600}" 9 || { echo "Failed to acquire lock for $squash_file" >&2; exit 1; }
             if unsquashfs -l "$squash_file" > /dev/null 2>&1; then
                 echo "Squash file already exists and is valid, skipping import: $squash_file"
             else

runners/launch_b200-nscale-slurm.sh

@@ -0,0 +1,14 @@
+#!/usr/bin/bash
+
+export SLURM_PARTITION="batch_1"
+export SLURM_ACCOUNT="benchmark"
+export MODEL_PATH="/scratch/models/Kimi-K2.6-NVFP4"
+
+export B200_SQUASH_DIR="/data/home/sa-shared/containers"
+export B200_SQUASH_LOCK_TIMEOUT="3600"
+mkdir -p "$B200_SQUASH_DIR" || {
+    echo "Unable to prepare nscale runner storage" >&2
+    exit 1
+}
+
+exec bash "$(dirname "${BASH_SOURCE[0]}")/launch_b200-dgxc.sh" "$@"