A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 10, 16:30 UTC
main
[Bugfix]: avoid overriding audio/text kwargs (Qwen3-Omni) (#31790)
Jzz1943 committed 10 months ago
[Misc] Implement `TokenizerLike.convert_tokens_to_ids` (#31796)
Cyrus Leung committed 10 months ago
[Bugfix] Fix torch.compile error for DP + MoE on CPU Backend (#31650)
kzwrime committed 10 months ago
Lucas Wilkinson committed 10 months ago
[Chore] Cleanup `mem_utils.py` (#31793)
Cyrus Leung committed 10 months ago
[Doc] Fix format of multimodal_inputs.md (#31800)
BlankR committed 10 months ago
[CI] Increase the MTEB_EMBED_TOL threshold to 5e-4. (#31797)
wang.yuqi committed 10 months ago
[Misc] Use `deprecated` for `seed_everything` (#31780)
Cyrus Leung committed 10 months ago
[cpu][bench] Add CPU paged attention benchmarks (#31720)
Fadi Arafeh committed 10 months ago
[Chore] Remove more V0 dead code from `sequence.py` (#31783)
Cyrus Leung committed 10 months ago
[Bugfix][CI/Build] Fix failing pooling models test due to Triton kernel accuracy diff (#31776)
Isotr0py committed 10 months ago
[Models]: Use `MMEncoderAttention` for MoonViT (#31738)
Isotr0py committed 10 months ago
vllmellm committed 10 months ago
[Doc] Show that `use_audio_in_video` is supported in docs (#30837)
Cyrus Leung committed 10 months ago
[Bugfix][Hardware][AMD] Fix exception types in AITER MLA FP8 check (#31177)
Kevin McKay committed 10 months ago
[CI] Fix CPU MM PRocessor Test (#31764)
Robert Shaw committed 10 months ago
[Bugfix] Add init_workspace_manager to moe kernel benchmarks (#31042)
Michael Goin committed 10 months ago
[UX] Add `-ep` shorthand for `--enable-expert-parallel` (#30890)
Michael Goin committed 10 months ago
[Cleanup] Remove redundant `decoder_layer_type` assignment in `Qwen2` (#31760)
maang committed 10 months ago
Wentao Ye committed 10 months ago