From 56e05c1ac517bf9964b21a0d20643aa7a5803f60 Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Wed, 28 Oct 2026 08:19:33 +0000 Subject: [PATCH 1/2] feat(minimaxm3): update B300 TensorRT-LLM AgentX MTP image to 1.4.0rc1 Pin nvcr.io/nvidia/tensorrt-llm/release:1.4.0rc1 by digest, rename kv_cache_config.block_reuse_policy to block_reuse_config.policy as the 1.4 KvCacheConfig requires, and drop the openai_protocol.py store=false patch hook because engine patches are not allowed. Co-Authored-By: Claude Opus 5.5 --- .../minimaxm3/trtllm/b300-fp4-mtp/agentic.yaml | 4 ++-- inferencex-e2e/configs/nvidia-master.yaml | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/minimaxm3/trtllm/b300-fp4-mtp/agentic.yaml b/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/minimaxm3/trtllm/b300-fp4-mtp/agentic.yaml index a5d7319918..db977bd887 100644 --- a/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/minimaxm3/trtllm/b300-fp4-mtp/agentic.yaml +++ b/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/minimaxm3/trtllm/b300-fp4-mtp/agentic.yaml @@ -14,7 +14,6 @@ base: engine: type: trtllm served_model_name: nvidia/MiniMax-M3-NVFP4 - setup_script: minimaxm3-trtllm-agentx.sh roles: agg: nodes: 1 @@ -45,7 +44,8 @@ base: kv_cache_config: free_gpu_memory_fraction: 0.94 enable_block_reuse: true - block_reuse_policy: per_conversation + block_reuse_config: + policy: per_conversation tokens_per_block: 128 use_kv_cache_manager_v2: true dtype: fp8 diff --git a/inferencex-e2e/configs/nvidia-master.yaml b/inferencex-e2e/configs/nvidia-master.yaml index dcc8d15576..b9a932e679 100644 --- a/inferencex-e2e/configs/nvidia-master.yaml +++ b/inferencex-e2e/configs/nvidia-master.yaml @@ -5529,7 +5529,7 @@ minimaxm3-fp4-gb300-dynamo-vllm-agentic-mtp-disagg: dp-attn: false decode: { num-worker: 5, tp: 2, ep: 1, dp-attn: false } minimaxm3-fp4-b300-trtllm-agentic-mtp: - image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc23.post1 + image: nvcr.io/nvidia/tensorrt-llm/release:1.4.0rc1@sha256:3bedbe0321e7eb5430f3177d88894a3cf2dc2f6a087d0e85c13fc882667c75c0 model: nvidia/MiniMax-M3-NVFP4 model-prefix: minimaxm3 runner: cluster:b300-dsxe From 1d372562968bf71eddc70e18f20d0f0f7f428937 Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Wed, 28 Oct 2026 10:11:02 +0000 Subject: [PATCH 2/2] perf-changelog: MiniMax-M3 FP4 B300 TensorRT-LLM AgentX MTP 1.4.0rc1 Co-Authored-By: Claude Opus 5.5 --- inferencex-e2e/perf-changelog.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml index 907bd21213..f3984b2aa6 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -11489,3 +11489,11 @@ - "Update the MI355X DeepSeek-V4-Pro-0813 SGLang MoRI disaggregated AgentX serving image from lmsysorg/sglang-rocm:v0.5.22-rocm720-mi35x-20261019 to lmsysorg/sglang-rocm:v0.5.22-rocm10-mi35x-20261026, the latest published MI35x ROCm 10 nightly (digest sha256:edabad83728ab04e3eae39f315eb16261eeb64dbdb051112bd22fc88560b60c4)." - "Preserve all eight concurrency points (1, 16, 32, 48, 192, 256, 384, 512), prefill/decode topology, DSpark settings, UMBP offload, MoRI transfer, and benchmark client image. The workload binder supplies the serving image to every selected recipe variant." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4571 + +- config-keys: + - minimaxm3-fp4-b300-trtllm-agentic-mtp + scenario-type: + - agentic-coding + description: + - "Update the MiniMax-M3 FP4 B300 TensorRT-LLM AgentX MTP image from 1.3.0rc23.post1 to 1.4.0rc1." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4607