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 12, 09:45 UTC
main
[BugFix] Fix new nightly failures (#29578)
Lucas Wilkinson committed 12 months ago
[Model Runner V2][BugFix] Keep reference to GPU tensors in AsyncOutput (#29623)
Woosuk Kwon committed 12 months ago
[BugFix] Fix `plan` API Mismatch when using latest FlashInfer (#29426)
Andrii Skliar committed 12 months ago
[CI] Add batched audios Whisper test (#29308)
Nicolò Lucchesi committed 12 months ago
[Bugfix][MM encoder] Fix ViT attention backend resolving for Turing GPU (#29614)
Isotr0py committed 12 months ago
[Deprecation] Advance deprecation status (#29617)
Cyrus Leung committed 12 months ago
[Misc] Remove unused code from `protocol.py` (#29616)
Cyrus Leung committed 12 months ago
add skip_reading_prefix_cache in repr for PoolingParams (#29620)
果冻虾仁 committed 12 months ago
[Bugfix] Fix doc build on main (#29619)
Cyrus Leung committed 12 months ago
[BugFix] Optional tokenizer argument when loading GGUF models (#29582)
Injae Ryou committed 12 months ago
Update Transformers pin in CI to 4.57.3 (#29418)
Harry Mellor committed 12 months ago
[Attention] Update attention imports (#29540)
Matthew Bonanni committed 12 months ago
[bugfix] avoid NIXL_ERR_REMOTE_DISCONNECT in nixl_connector when Prefill dies (#28120)
Mathis Felardos committed 12 months ago
[Doc]: fixing typos in diverse files (#29492)
Didier Durand committed 12 months ago
[CI/Build] Skip ray tests on ROCm (#29556)
Ryan Rock committed 12 months ago
[CI/Build][Bugfix] Fix auto label issues for CPU (#29610)
Li, Jiang committed 12 months ago
[LoRA] Continue optimizing MoE LoRA weight loading (#29322)
Jee Jee Li committed 12 months ago
[Bugfix] Fix HunyuanVL XD-RoPE (#29593)
Roger Wang committed 12 months ago
[CI] Auto label CPU related issues (#29602)
Li, Jiang committed 12 months ago
[Bugfix] Fix pre-commit (#29601)
Cyrus Leung committed 12 months ago