Skip to content

[Klaud Cold] Update MiniMax-M3 FP4 B300 TensorRT-LLM AgentX MTP image to 1.4.0rc1 / [Klaud Cold] 将 MiniMax-M3 FP4 B300 TensorRT-LLM AgentX MTP 镜像更新至 1.4.0rc1 #4607

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Klaud-Cold wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[Klaud Cold] Update MiniMax-M3 FP4 B300 TensorRT-LLM AgentX MTP image to 1.4.0rc1 / [Klaud Cold] 将 MiniMax-M3 FP4 B300 TensorRT-LLM AgentX MTP 镜像更新至 1.4.0rc1 #4607

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
56e05c1
feat(minimaxm3): update B300 TensorRT-LLM AgentX MTP image to 1.4.0rc1
github-actions[bot] Oct 28, 2026
1d37256
perf-changelog: MiniMax-M3 FP4 B300 TensorRT-LLM AgentX MTP 1.4.0rc1
github-actions[bot] Oct 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions ...x-e2e/benchmarks/single_node/srt-slurm-recipes/minimaxm3/trtllm/b300-fp4-mtp/agentic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,6 @@ base:
engine:
type: trtllm
served_model_name: nvidia/MiniMax-M3-NVFP4

@claude claude Bot Oct 28, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🔴 If TRT-LLM 1.4.0rc1 still lacks a store chat field, BFCL eval runs on this B300 key will get request-validation errors that the base image's patch prevented. Removing setup_script: minimaxm3-trtllm-agentx.sh also removes the only step that adds store: Optional[Literal[False]] to ChatCompletionRequest. Nothing in this PR shows the new image accepts store=false natively. Fix: before dropping the hook, confirm 1.4.0rc1's serve/openai_protocol.py accepts store. If it does not, keep the hook, as the b200-fp4-mtp recipe still does.

Why this was flagged

The removed hook is minimaxm3-trtllm-agentx.sh (multi_node/srt-slurm-recipes/configs/minimaxm3-trtllm-agentx.sh:8). It runs runners/patch_trtllm_chat_store.py, which inserts store: Optional[Literal[False]] = False into TensorRT-LLM's ChatCompletionRequest. The trigger is an explicit BFCL suite (bfcl_smoke or bfcl_vllm_minimax_m3 in infx/bench/eval/vendor.py:348-352) run against minimaxm3-fp4-b300-trtllm-agentic-mtp. BFCL's OpenAI client sends store=false. On the base image the hook adds the field, so those requests are accepted. With this diff there is no hook. If 1.4.0rc1's protocol model still rejects unknown fields and has no store field, every BFCL chat request is rejected and the eval fails or scores 0. The perf-changelog entry describes only the image bump and does not mention the dropped hook.

Verification: The diff deletes setup_script: minimaxm3-trtllm-agentx.sh from b300-fp4-mtp/agentic.yaml, at old line 17. runners/patch_trtllm_chat_store.py:13 inserts store: Optional[Literal[False]] = False into ChatCompletionRequest in tensorrt_llm/serve/openai_protocol.py. If the new image still has no store field, every BFCL tool-use request to this key goes back to failing with HTTP 400.

setup_script: minimaxm3-trtllm-agentx.sh
roles:
agg:
nodes: 1
Expand Down Expand Up @@ -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
Expand Down
2 changes: 1 addition & 1 deletion inferencex-e2e/configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
8 changes: 8 additions & 0 deletions inferencex-e2e/perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Loading