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 15, 18:30 UTC
main
[Docs] Annouce Ollama and Singapore Meetups (#15161)
Simon Mo committed over 1 year ago
[FrontEnd][Perf] `merge_async_iterators` fast-path for single-prompt requests (#15150)
Nick Hill committed over 1 year ago
[V1][TPU] Change kv cache shape. (#15145)
iefgnoix committed over 1 year ago
simple bugfix: Update stats.py (#15139)
Wang Ran (汪然) committed over 1 year ago
[FEAT]Support reset prefix cache by specified device (#15003)
maobaolong committed over 1 year ago
[V1] Minor V1 async engine test refactor (#15075)
Murali Andoorveedu committed over 1 year ago
[Frontend] Remove custom_cache_manager (#13791)
Alessandro Sangiorgi committed over 1 year ago
[Misc] Update the "the first vLLM China Meetup" slides link to point to the first page (#15134)
Kero Liang committed over 1 year ago
[Bugfix] Adjust mllama to regional compilation (#15112)
Jan Kaniecki committed over 1 year ago
[Misc][Benchmark] Add support for different `tokenizer_mode` (#15040)
Aaron Pham committed over 1 year ago
[Doc] Update tip info on using latest transformers when creating a custom Dockerfile (#15070)
Marc-Alexandre Côté committed over 1 year ago
[Bugfix] Fix size calculation of processing cache (#15114)
Cyrus Leung committed over 1 year ago
[Misc] Avoid unnecessary HF `do_rescale` warning when passing dummy data (#15107)
Cyrus Leung committed over 1 year ago
[V1][Bugfix] Fix oracle for device checking (#15104)
Roger Wang committed over 1 year ago
[CI][Intel GPU] update XPU dockerfile and CI script (#15109)
Kunshang Ji committed over 1 year ago
[Bugfix] Re-enable Gemma3 for V1 (#14980)
Cyrus Leung committed over 1 year ago
[V1] Ensure using int64 for sampled token ids (#15065)
Woosuk Kwon committed over 1 year ago
[Core] Update dtype detection and defaults (#14858)
Cyrus Leung committed over 1 year ago
[Model] Remove duplicated message check in Mistral chat completion request (#15069)
Brayden Zhong committed over 1 year ago
[Model] Pixtral: Remove layer instantiation duplication (#15053)
Julien Denize committed over 1 year ago