Skip to content

[docker] backport output-gate slicing when query groups < TP - #2221

Open
LLMShark wants to merge 1 commit into
THUDM:mainfrom
LLMShark:agent/fix-qwen35-output-gate-tp
Open

[docker] backport output-gate slicing when query groups < TP#2221
LLMShark wants to merge 1 commit into
THUDM:mainfrom
LLMShark:agent/fix-qwen35-output-gate-tp

fix(docker): slice output gate for GQA TP

04f5038
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning
agent-test (0, test_agent/test_adapters.py)
succeeded Jul 20, 2026 in 57s