diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index 90a430b9d..f3eb01ad3 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -3537,21 +3537,20 @@ minimaxm2.5-fp4-b200-vllm:
   - isl: 1024
     osl: 1024
     search-space:
-    - { tp: 1, conc-start: 4, conc-end: 4 }
-    - { tp: 2, conc-start: 4, conc-end: 512 }
-    - { tp: 2, ep: 2, conc-start: 128, conc-end: 256 }
-    - { tp: 2, ep: 2, dp-attn: true, conc-start: 512, conc-end: 512 }
-    - { tp: 4, conc-start: 4, conc-end: 512 }
-    - { tp: 4, ep: 4, conc-start: 32, conc-end: 128 }
-    - { tp: 8, conc-start: 4, conc-end: 4 }
+    - { tp: 1, conc-start: 4, conc-end: 16 }
+    - { tp: 2, conc-start: 16, conc-end: 16 }
+    - { tp: 2, ep: 2, conc-start: 128, conc-end: 128 }
+    - { tp: 2, ep: 2, dp-attn: true, conc-start: 256, conc-end: 1024 }
+    - { tp: 4, conc-start: 4, conc-end: 16 }
+    - { tp: 4, ep: 4, conc-start: 64, conc-end: 128 }
+    - { tp: 8, conc-start: 4, conc-end: 8 }
   - isl: 8192
     osl: 1024
     search-space:
     - { tp: 1, conc-start: 4, conc-end: 32 }
-    - { tp: 1, conc-start: 256, conc-end: 512 }
-    - { tp: 2, conc-start: 4, conc-end: 512 }
+    - { tp: 1, conc-start: 256, conc-end: 256 }
     - { tp: 2, ep: 2, conc-start: 128, conc-end: 512 }
-    - { tp: 4, conc-start: 4, conc-end: 512 }
+    - { tp: 4, conc-start: 4, conc-end: 8 }
     - { tp: 8, conc-start: 4, conc-end: 4 }
 
 # NOTE: At the time of submission, https://docs.vllm.ai/projects/recipes/en/latest/MiniMax/MiniMax-M2.html
diff --git a/benchmarks/single_node/minimaxm2.5_fp4_b200.sh b/benchmarks/single_node/minimaxm2.5_fp4_b200.sh
index 7cd107a4d..aae5886e1 100755
--- a/benchmarks/single_node/minimaxm2.5_fp4_b200.sh
+++ b/benchmarks/single_node/minimaxm2.5_fp4_b200.sh
@@ -25,6 +25,8 @@ hf download "$MODEL"
 SERVER_LOG=/workspace/server.log
 PORT=${PORT:-8888}
 
+export VLLM_FLOAT32_MATMUL_PRECISION=high
+
 if [ "${DP_ATTENTION}" = "true" ]; then
   PARALLEL_ARGS="--tensor-parallel-size=1 --data-parallel-size=$TP --enable-expert-parallel"
 elif [ "$EP_SIZE" -gt 1 ]; then
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index ac0ef5d79..21c299045 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1638,3 +1638,9 @@
   description:
     - "Add kv-cache-dtype fp8, max-cudagraph-capture-size 2048, max-num-batched-tokens, and stream-interval 20 to server launch args"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1047
+
+- config-keys:
+    - minimaxm2.5-fp4-b200-vllm
+  description:
+    - "Add VLLM_FLOAT32_MATMUL_PRECISION=high"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1069