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 16, 03:15 UTC
main
[misc] remove python function call for custom activation op (#11885)
cennn committed almost 2 years ago
youkaichao committed almost 2 years ago
[BUGFIX] Fix `UnspecifiedPlatform` package name (#11916)
Kunshang Ji committed almost 2 years ago
[Bugfix] Validate lora adapters to avoid crashing server (#11727)
Joe Runde committed almost 2 years ago
[torch.compile] Hide KV cache behind torch.compile boundary (#11677)
Chen Zhang committed almost 2 years ago
[Doc] Show default pooling method in a table (#11904)
Cyrus Leung committed almost 2 years ago
[VLM] Enable tokenized inputs for merged multi-modal processor (#11900)
Cyrus Leung committed almost 2 years ago
[Doc][5/N] Move Community and API Reference to the bottom (#11896)
Cyrus Leung committed almost 2 years ago
[Docs] Add Modal to deployment frameworks (#11907)
Charles Frye committed almost 2 years ago
[Misc] Provide correct Pixtral-HF chat template (#11891)
Cyrus Leung committed almost 2 years ago
[ci]try to fix flaky multi-step tests (#11894)
youkaichao committed almost 2 years ago
[platform] Allow platform specify attention backend (#11609)
wangxiyuan committed almost 2 years ago
[Doc] Add model development API Reference (#11884)
Cyrus Leung committed almost 2 years ago
[Bugfix] fix beam search input errors and latency benchmark script (#11875)
Ye (Charlotte) Qi committed almost 2 years ago
[Bugfix] Override dunder methods of placeholder modules (#11882)
Cyrus Leung committed almost 2 years ago
[perf]fix current stream (#11870)
youkaichao committed almost 2 years ago
[Doc] Intended links Python multiprocessing library (#11878)
Guspan Tanadi committed almost 2 years ago
[Misc] Move `print_*_once` from utils to logger (#11298)
Cyrus Leung committed almost 2 years ago
[Doc] Recommend uv and python 3.12 for quickstart guide (#11849)
Michael Goin committed almost 2 years ago
treat do_lower_case in the same way as the sentence-transformers library (#11815)
Maximilien de Bayser committed almost 2 years ago