Merge main into GB200 FP8 MiniMax PR

Author: jasonlizhengjian

.github/configs/nvidia-master.yaml

@@ -9067,7 +9067,7 @@ glm5-fp8-b200-dynamo-sglang:
 
 # MTP variant of dsv4-fp4-gb300-dynamo-sglang.
 dsv4-fp4-gb300-dynamo-sglang-mtp:
-  image: lmsysorg/sglang:nightly-dev-cu13-20260509-9ee83034
+  image: lmsysorg/sglang:nightly-dev-20260527-14f81a67
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: gb300-cw

perf-changelog.yaml

@@ -3404,6 +3404,13 @@
     - "Add DeepSeek-V4-Pro FP4 MI355X ATOM MTP3 benchmark; image rocm/atom:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.3"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1627
 
+- config-keys:
+    - dsv4-fp4-gb300-dynamo-sglang-mtp
+  description:
+    - "Update SGLang image from nightly-dev-cu13-20260509-9ee83034 to nightly-dev-20260527-14f81a67"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1637
+
+
 - config-keys:
     - minimaxm2.5-fp4-gb200-dynamo-vllm
   description:
@@ -3431,6 +3438,13 @@
     - "Same 1k/1k and 8k/1k search space as gb300, plus a new tp8-1p1d at low concurrencies for both ISLs"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1652
 
+- config-keys:
+    - minimaxm2.5-fp4-gb300-dynamo-vllm
+  description:
+    - "Add MiniMax-M2.5 NVFP4 GB300 disaggregated multinode vLLM benchmarks via Dynamo"
+    - "Add 1k1k/8k1k minimax recipe set under benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m2.5/"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1641
+
 - config-keys:
     - minimaxm2.5-fp8-gb200-dynamo-vllm
   description: