Paul Zhang e7acb20076

[Feature] Batch invariant torch.compile (#27660) ...

Signed-off-by: PaulZhang12 <paulzhan@fb.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

2025-10-30 13:11:29 -07:00

..

__init__.py

…

cache.py

[Bugfix] mamba-block-size is set for vision language model (#27773)

2025-10-29 19:39:57 -07:00

compilation.py

[Model] Introduce Kimi Linear to vLLM (#27809)

2025-10-30 21:02:27 +08:00

device.py

…

kv_events.py

[Feature] publisher default set zmq in kv_event config (#26915)

2025-10-22 19:19:33 +00:00

kv_transfer.py

Fix typo in ValueError message: use kv_role instead of kv_disagg_role (#27166)

2025-10-19 19:47:19 +00:00

load.py

…

lora.py

[V0 deprecation] Remove VLLM_USE_V1 usage in config module (#27784)

2025-10-30 09:42:49 +00:00

model.py

[Feature] Batch invariant torch.compile (#27660)

2025-10-30 13:11:29 -07:00

multimodal.py

[Frontend] Require flag for loading text and image embeds (#27204)

2025-10-22 15:52:02 +00:00

observability.py

…

parallel.py

[Bugfix] Improve GPU validation logging in Ray fallback scenarios (#25775)

2025-10-30 11:57:59 +00:00

pooler.py

[Frontend][Doc][5/N] Improve all pooling task | Polish encode (pooling) api & Document. (#25524)

2025-10-30 12:13:05 +00:00

scheduler.py

[MISC] cudagraph_capture_sizes related improvements (#26016)

2025-10-24 05:11:05 -07:00

speculative.py

[V0 deprecation] Remove VLLM_USE_V1 usage in config module (#27784)

2025-10-30 09:42:49 +00:00

speech_to_text.py

…

structured_outputs.py

…

utils.py

[CI/Build] Move pre-commit only scripts to tools/pre_commit (#27657)

2025-10-29 08:04:33 +00:00

vllm.py

[CI] Fix mypy for vllm/v1/core and vllm/v1/engine (#27108)

2025-10-30 11:32:17 +00:00