Merge branch 'main' into chun-uma/gptoss-regression-fix-1

Author: chunfangamd

benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp8_h200.sh

@@ -42,6 +42,14 @@ else
   EP=()
 fi
 
+if [ "$ISL" = "8192" ]; then
+  ATTN_BACKEND="FLASH_ATTN"
+  AUTOTUNE_FLAG=()
+else
+  ATTN_BACKEND="FLASHINFER"
+  AUTOTUNE_FLAG=(--enable-flashinfer-autotune)
+fi
+
 # Start GPU monitoring (power, temperature, clocks every second)
 start_gpu_monitor
 
@@ -55,8 +63,8 @@ vllm serve "$MODEL" --port "$PORT" \
 --max-num-batched-tokens "$MAX_NUM_BATCHED_TOKENS" \
 --kv-cache-dtype fp8 \
 --moe-backend triton \
---attention-backend FLASHINFER \
---enable-flashinfer-autotune \
+--attention-backend "$ATTN_BACKEND" \
+"${AUTOTUNE_FLAG[@]}" \
 --compilation-config "$COMPILATION_CONFIG" \
 --no-enable-prefix-caching \
 --trust-remote-code > "$SERVER_LOG" 2>&1 &

perf-changelog.yaml

@@ -3475,8 +3475,16 @@
     - "Set max-running-requests=256, chunked-prefill-size=16384, mem-fraction-static=0.8, cuda-graph-max-bs=CONC, and enable symm-mem"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1544
 
+- config-keys:
+    - minimaxm2.5-fp8-h200-vllm
+  description:
+    - "Switch attention backend from FLASHINFER to FLASH_ATTN for the 8k/1k cell of MiniMax-M2.5 FP8 H200 vLLM."
+    - "1k/1k cell not changed in this PR: at 1k/1k all three measured configs."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1668
+
 - config-keys:
     - gptoss-fp4-mi355x-vllm
   description:
     - "Update GPT-OSS model for MI355X vLLM from amd/gpt-oss-120b-w-mxfp4-a-fp8 to openai/gpt-oss-120b"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1670
+