diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index a02749d4d..3bb3203d4 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -4358,7 +4358,7 @@ minimaxm2.5-fp8-b200-vllm-agentic:
   # MiniMax-M2.5 FP8 B200 vLLM recipe as-is until B300-specific tuning is available.
 
 minimaxm2.5-fp8-b300-vllm:
-  image: vllm/vllm-openai:v0.21.0
+  image: vllm/vllm-openai:v0.22.0
   model: MiniMaxAI/MiniMax-M2.5
   model-prefix: minimaxm2.5
   runner: b300
@@ -4462,7 +4462,7 @@ minimaxm2.5-fp4-b200-vllm-agentic:
   # MiniMax-M2.5 FP4 B200 vLLM recipe as-is until B300-specific tuning is available.
 
 minimaxm2.5-fp4-b300-vllm:
-  image: vllm/vllm-openai:v0.21.0
+  image: vllm/vllm-openai:v0.22.0
   model: nvidia/MiniMax-M2.5-NVFP4
   model-prefix: minimaxm2.5
   runner: b300
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp4_b200.sh b/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp4_b200.sh
index fc7877a1c..315d3a439 100755
--- a/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp4_b200.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp4_b200.sh
@@ -25,6 +25,7 @@ if [[ "$MODEL" != /* ]]; then hf download "$MODEL"; fi
 SERVER_LOG=/workspace/server.log
 
 export VLLM_FLOAT32_MATMUL_PRECISION=high
+export VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0
 
 if [ "${DP_ATTENTION}" = "true" ]; then
   PARALLEL_ARGS="--tensor-parallel-size=1 --data-parallel-size=$TP --enable-expert-parallel"
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp4_b300.sh b/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp4_b300.sh
index 33492aada..62459b8b0 100755
--- a/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp4_b300.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp4_b300.sh
@@ -40,6 +40,7 @@ nvidia-smi
 SERVER_LOG=/workspace/server.log
 
 export VLLM_FLOAT32_MATMUL_PRECISION=high
+export VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0
 
 if [ "${DP_ATTENTION}" = "true" ]; then
   PARALLEL_ARGS="--tensor-parallel-size 1 --data-parallel-size $TP --enable-expert-parallel"
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp8_b200.sh b/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp8_b200.sh
index 9897afca3..10f6f4e6f 100755
--- a/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp8_b200.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp8_b200.sh
@@ -24,6 +24,7 @@ if [[ "$MODEL" != /* ]]; then hf download "$MODEL"; fi
 SERVER_LOG=/workspace/server.log
 
 export VLLM_FLOAT32_MATMUL_PRECISION=high
+export VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0
 
 if [ "$EP_SIZE" -gt 1 ]; then
   EP=" --enable-expert-parallel"
diff --git a/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp8_b300.sh b/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp8_b300.sh
index 14e853ce9..e2c1bbc05 100755
--- a/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp8_b300.sh
+++ b/benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp8_b300.sh
@@ -39,6 +39,7 @@ nvidia-smi
 SERVER_LOG=/workspace/server.log
 
 export VLLM_FLOAT32_MATMUL_PRECISION=high
+export VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0
 
 if [ "$EP_SIZE" -gt 1 ]; then
   EP=" --enable-expert-parallel"
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 5622173f1..bc3c1c19a 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3531,3 +3531,13 @@
     - "The Rust frontend replaces only the Python serving/API layer (HTTP, tokenization, scheduling glue, detokenization) and spawns the same Python EngineCore, so GPU kernels/attention/MoE GEMM/KV cache are untouched"
     - "A/B sweep (28 single-node points, 1k1k + 8k1k, TP 1/2/4) vs the Python-frontend baseline (run 26696260751): throughput Pareto-neutral (peak tok/s/GPU within <1.5%, frontiers coincident) and TPOT flat (+-0.5%); TTFT improves ~8% at 1k1k and ~22% at 8k1k (every point), the expected signature of lower frontend CPU latency before first token, scaling with input length"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1634
+
+- config-keys:
+    - minimaxm2.5-fp8-b200-vllm
+    - minimaxm2.5-fp8-b300-vllm
+    - minimaxm2.5-fp4-b200-vllm
+    - minimaxm2.5-fp4-b300-vllm
+  description:
+    - "Use vLLM image v0.22.0 for MiniMax-M2.5 FP8/FP4 B200/B300 aggregate benchmarks."
+    - "Set VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0 in the B200/B300 MiniMax aggregate launch scripts."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1704