Merge branch 'main' into codex-split-attention-offload-guides

This commit is contained in:
Hongsheng Liu authored and GitHub committed 2026-08-15 07:00:22 +08:00
commit 7ec78360bb
335 files changed
+26588 -2909

No files matched your search

+3
View File
@@ -73,6 +73,8 @@ plugins:
- awesome-nav
- redirects:
redirect_maps:
community/meetups.md: community/meetings.md
community/volunteers.md: community/contact_us.md
user_guide/diffusion/request_batching.md: user_guide/diffusion/execution_modes.md
user_guide/diffusion/step_execution.md: user_guide/diffusion/execution_modes.md
user_guide/diffusion/cpu_offload_diffusion.md: user_guide/diffusion/cpu_offload.md
@@ -115,6 +117,7 @@ plugins:
- "vllm_omni.entrypoints.openai" # avoid importing vllm in mkdocs building
- "vllm_omni.entrypoints.openai.protocol" # avoid importing vllm in mkdocs building
- "vllm_omni.experimental" # avoid importing optional serving deps (openai, fastapi, uvicorn, httpx) in mkdocs building
- "vllm_omni.model_executor.models.nemotron_voicechat.nemo_vendored" # vendored NeMo code; upstream docstrings trip griffe strict warnings
- mkdocstrings:
handlers:
python: