Skip to content

config(minimaxm3): refresh full GB200 aggregate AgentX curve / 刷新完整 GB200 聚合 AgentX 曲线 #2806

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

Closed
RohitNagraj wants to merge 4 commits into from
+13 −0
Closed

config(minimaxm3): refresh full GB200 aggregate AgentX curve / 刷新完整 GB200 聚合 AgentX 曲线 #2806

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e0c832a
config(minimaxm3): update GB200 aggregate recipes
RohitNagraj Sep 2, 2026
4a50379
fix(minimaxm3): align aggregate GQA acceptance target
RohitNagraj Sep 2, 2026
f9dcf6c
fix(minimaxm3): share backend model cache
RohitNagraj Sep 2, 2026
d8d4221
fix(minimaxm3): restore full aggregate sweep
RohitNagraj Sep 2, 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
3 changes: 3 additions & 0 deletions ...node/srt-slurm-recipes/vllm/minimax-m3/gb200-fp4/agentic/agg-tp4-vllm-simple-agentic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,9 @@ backend:
connector: null
kv_events_config: { aggregated: true }
aggregated_environment:
HF_HUB_CACHE: "/hf_hub_cache"
HUGGINGFACE_HUB_CACHE: "/hf_hub_cache"
TRANSFORMERS_CACHE: "/hf_hub_cache"
VLLM_ENGINE_READY_TIMEOUT_S: "7200"
VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS: "1800"
VLLM_FLOAT32_MATMUL_PRECISION: "high"
Expand Down
10 changes: 10 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6821,3 +6821,13 @@
description:
- "Refresh to collect TensorRT-LLM server metrics."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2774

- config-keys:
- minimaxm3-fp4-gb200-dynamo-vllm-agentic-agg-mtp
scenario-type:
- agentic-coding
description:
- "Refresh the full GB200 aggregate Dynamo-vLLM AgentX configuration."
- "Use the mounted Hugging Face cache for the TP4 SimpleCPU-offload backend."
- "Use the committed MiniMax-M3 thinking-on EAGLE3-GQA acceptance target."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2806
Loading