diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_b300.sh b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_b300.sh
index da575147c..f91419edb 100755
--- a/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_b300.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm3_fp4_b300.sh
@@ -38,6 +38,7 @@ 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"
@@ -56,8 +57,9 @@ start_gpu_monitor
 set -x
 vllm serve "$MODEL_PATH" --served-model-name "$MODEL" --host 0.0.0.0 --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 60bac4b6d..278f40715 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -12809,7 +12809,7 @@ minimaxm3-fp8-b300-vllm:
 # weights are pre-staged read-only at /scratch/models/MiniMax-M3-NVFP4 (added to
 # the STAGED_MODELS allow-list in launch_b300-nv.sh).
 minimaxm3-fp4-b300-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: b300
@@ -12821,22 +12821,19 @@ minimaxm3-fp4-b300-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: 8, conc-start: 1, conc-end: 2 }
+      - { tp: 4, conc-start: 1, conc-end: 2 }
+      - { tp: 2, conc-start: 4, conc-end: 256 }
+      - { tp: 4, conc-start: 64, 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: 2, ep: 2, conc-start: 16, conc-end: 128 }
-      - { tp: 8, ep: 8, dp-attn: true, conc-start: 256, conc-end: 1024 }
+      - { tp: 2, ep: 2, dp-attn: true, conc-start: 512, conc-end: 512 }
     - isl: 8192
       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: 128 }
-      - { 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: 2 }
+      - { tp: 4, conc-start: 1, conc-end: 2 }
+      - { tp: 2, conc-start: 4, conc-end: 256 }
+      - { tp: 2, ep: 2, dp-attn: true, conc-start: 512, conc-end: 512 }
 
 # EAGLE3 speculative-decoding (spec-decoding: mtp) variant of MiniMax-M3 NVFP4
 # (nvidia/MiniMax-M3-NVFP4) B300 single-node vLLM, pairing the target with the
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 818092577..705a363eb 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4426,3 +4426,10 @@
     - "Use 1k/1k TP4/EP1 c1-c32 and TP4/EP4 c64-c256; use 8k/1k TP4/EP1 c1-c32 and TP4/EP4 DP-attention c64-c256."
     - "Drop the TP8/EP8 single-concurrency points."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1975
+
+- config-keys:
+    - minimaxm3-fp4-b300-vllm
+  description:
+    - "Update Minimax M3 b300 vllm image tag"
+    - "Update search space to cover more configs"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1990