diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index 776413032..59a1ec753 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -3513,9 +3513,8 @@ minimaxm2.5-fp8-b200-vllm:
   - isl: 1024
     osl: 1024
     search-space:
-    - { tp: 2, conc-start: 4, conc-end: 512 }
-    - { tp: 4, conc-start: 4, conc-end: 512 }
     - { tp: 2, ep: 2, conc-start: 512, conc-end: 512 }
+    - { tp: 4, conc-start: 4, conc-end: 128 }
     - { tp: 4, ep: 4, conc-start: 256, conc-end: 512 }
   - isl: 8192
     osl: 1024
diff --git a/benchmarks/single_node/minimaxm2.5_fp8_b200.sh b/benchmarks/single_node/minimaxm2.5_fp8_b200.sh
index d892d72f1..0ba6437c4 100755
--- a/benchmarks/single_node/minimaxm2.5_fp8_b200.sh
+++ b/benchmarks/single_node/minimaxm2.5_fp8_b200.sh
@@ -24,7 +24,7 @@ hf download "$MODEL"
 SERVER_LOG=/workspace/server.log
 PORT=${PORT:-8888}
 
-export VLLM_FLASHINFER_ALLREDUCE_BACKEND=mnnvl
+export VLLM_FLOAT32_MATMUL_PRECISION=high
 
 if [ "$EP_SIZE" -gt 1 ]; then
   EP=" --enable-expert-parallel"
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index cc9baf1c0..552bdd7ab 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1690,3 +1690,9 @@
   description:
     - "Add VLLM_FLOAT32_MATMUL_PRECISION=high, update search space concurrency ranges"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1107
+
+- config-keys:
+    - minimaxm2.5-fp8-b200-vllm
+  description:
+    - "Add VLLM_FLOAT32_MATMUL_PRECISION=high, remove VLLM_FLASHINFER_ALLREDUCE_BACKEND=mnnvl"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1068