diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_b200.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_b200.sh
index 9abaf33af..966448b0c 100755
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_b200.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_b200.sh
@@ -33,6 +33,7 @@ SERVER_LOG=/workspace/server.log
 
 export VLLM_ENGINE_READY_TIMEOUT_S=3600
 export VLLM_FLOAT32_MATMUL_PRECISION=high
+export VLLM_FLASHINFER_ALLREDUCE_BACKEND=trtllm
 
 if [ "${DP_ATTENTION}" = "true" ]; then
   PARALLEL_ARGS="--tensor-parallel-size=1 --data-parallel-size=$TP --enable-expert-parallel"
@@ -51,8 +52,9 @@ start_gpu_monitor
 set -x
 vllm serve $MODEL --port $PORT \
 $PARALLEL_ARGS \
---gpu-memory-utilization 0.90 \
+--gpu-memory-utilization 0.95 \
 --max-model-len $MAX_MODEL_LEN \
+--kv-cache-dtype fp8 \
 --block-size 128 \
 --language-model-only \
 --max-cudagraph-capture-size 2048 \
diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 278f40715..a23ebe349 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -12917,7 +12917,7 @@ minimaxm3-fp8-b200-vllm:
 # (MSA sparse/index cache); weights are pre-staged at /scratch/fsw/models/MiniMax-M3-NVFP4
 # (launch_b200-dgxc.sh resolves MODEL_PATH for minimaxm3-fp4).
 minimaxm3-fp4-b200-vllm:
-  image: vllm/vllm-openai:vllm-minimax-m3-perf-x86_64-13.0.1-8b00f41
+  image: vllm/vllm-openai:nightly-93d8f834dd8acf33eb0e2a75b2711b628cb6e226
   model: nvidia/MiniMax-M3-NVFP4
   model-prefix: minimaxm3
   runner: b200-dgxc
@@ -12929,21 +12929,18 @@ minimaxm3-fp4-b200-vllm:
     - isl: 1024
       osl: 1024
       search-space:
-      - { tp: 8, conc-start: 1, conc-end: 64 }
-      - { tp: 8, ep: 8, conc-start: 1, conc-end: 512 }
-      - { tp: 4, conc-start: 1, conc-end: 64 }
-      - { tp: 4, ep: 4, conc-start: 64, conc-end: 512 }
-      - { tp: 4, ep: 4, dp-attn: true, conc-start: 128, conc-end: 512 }
-      - { tp: 8, ep: 8, dp-attn: true, conc-start: 256, conc-end: 1024 }
+      - { tp: 8, conc-start: 1, conc-end: 8 }
+      - { tp: 2, conc-start: 4, conc-end: 8 }
+      - { tp: 2, conc-start: 256, conc-end: 2048 }
+      - { tp: 4, conc-start: 32, conc-end: 256 }
     - isl: 8192
       osl: 1024
       search-space:
-      - { tp: 8, conc-start: 1, conc-end: 64 }
-      - { tp: 8, ep: 8, conc-start: 1, conc-end: 256 }
-      - { tp: 4, conc-start: 1, conc-end: 64 }
-      - { tp: 4, ep: 4, conc-start: 64, conc-end: 256 }
-      - { tp: 4, ep: 4, dp-attn: true, conc-start: 64, conc-end: 128 }
-      - { tp: 8, ep: 8, dp-attn: true, conc-start: 128, conc-end: 256 }
+      - { tp: 8, conc-start: 1, conc-end: 4 }
+      - { tp: 4, conc-start: 1, conc-end: 4 }
+      - { tp: 2, conc-start: 1, conc-end: 128 }
+      - { tp: 4, conc-start: 256, conc-end: 1024 }
+      - { tp: 4, ep: 4, dp-attn: true, conc-start: 256, conc-end: 1024 }
 
 # EAGLE3 speculative-decoding (spec-decoding: mtp) variant of
 # minimaxm3-fp8-b200-vllm, pairing MiniMaxAI/MiniMax-M3-MXFP8 with the
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 705a363eb..943f4b390 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4433,3 +4433,10 @@
     - "Update Minimax M3 b300 vllm image tag"
     - "Update search space to cover more configs"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1990
+
+- config-keys:
+    - minimaxm3-fp4-b200-vllm
+  description:
+    - "Update Minimax M3 b200 vllm image tag"
+    - "Update search space to cover more configs"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1978