[AgentX nightly] minimaxm3 MI300X FP8 vllm mtp / [AgentX nightly] minimaxm3 MI300X FP8 vllm 升级每日构建

inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/minimaxm3/vllm/mi300x-fp8-mtp/agentic.yaml

@@ -5,7 +5,7 @@ base:
   name: minimaxm3-fp8-mi300x-vllm-agentic
   model:
     path: hf:MiniMaxAI/MiniMax-M3-MXFP8
-    container: vllm/vllm-openai-rocm:v0.30.0
+    container: vllm/vllm-openai-rocm:nightly-5555a2d8f7116b2b4877f66516f4128176cf722a@sha256:e0be00f1b99da608cc3c8571c7c86bae0c05f19e1e61a59c1d70aeea6bca6140
     precision: fp8
   resources:
     gpu_type: mi300x

inferencex-e2e/configs/amd-master.yaml

@@ -1033,7 +1033,7 @@ dsr1-fp4-mi355x-sglang-disagg-mtp:
         decode: {num-worker: 1, tp: 8, ep: 8, dp-attn: true}
 
 minimaxm3-fp8-mi300x-vllm-agentic-mtp:
-  image: vllm/vllm-openai-rocm:v0.30.0
+  image: vllm/vllm-openai-rocm:nightly-5555a2d8f7116b2b4877f66516f4128176cf722a@sha256:e0be00f1b99da608cc3c8571c7c86bae0c05f19e1e61a59c1d70aeea6bca6140
   model: MiniMaxAI/MiniMax-M3-MXFP8
   model-prefix: minimaxm3
   runner: cluster:mi300x-amd

inferencex-e2e/perf-changelog.yaml

@@ -9683,3 +9683,10 @@
     - "TP2 c16/c32: 16K prefill chunks with decoder SWA bounded replay and the prefill CUDA graph disabled, a 96/48-step prefill-decode interval, PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True and 4 tokenizer workers; SGLANG_NUMA_BIND_V2=0 at c16 (previously 4K chunks with the default 16-step interval). Local one-hour runs on the new image: c16 55,560 tok/s/GPU at 264.6 tok/s/user P90 (324.9 median); c32 113,613 at 183.1 (242.7)."
     - "c64 and c128 move from TP2 to DEP2 (TP2/DP2/EP2 with DP attention, DP LM head and MegaMoE) behind sglang-router (cache_aware, dp-aware, routing key from the AIPerf correlation id), with total_requests load balancing, shortest-prefill-first scheduling, 16K chunks, 4096 SWA prefix tails and 4 tokenizer workers. c64 uses a 24-step prefill-decode interval and admits 128; c128 a 16-step interval, mem-fraction-static 0.85, admits 256 with a 128 graph batch. Local one-hour runs: c64 200,265 tok/s/GPU at 114.3 tok/s/user P90 (132.7 median), versus 149,666 at 99.4 median for the TP2 point it replaces; c128 271,364 at 81.6 P90 (93.0 median), versus 147,763 at 37.9 median."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3859
+
+- config-keys:
+  - minimaxm3-fp8-mi300x-vllm-agentic-mtp
+  description:
+  - Pin minimaxm3 MI300X FP8 vllm mtp AgentX to the 2026-10-13 image vllm/vllm-openai-rocm:nightly-5555a2d8f7116b2b4877f66516f4128176cf722a@sha256:e0be00f1b99da608cc3c8571c7c86bae0c05f19e1e61a59c1d70aeea6bca6140.
+  - Preserve deployment topology, speculative mode, concurrency points, KV-offload settings and evaluation coverage.
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3986