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, 07:00 UTC
main
[Doc] fix link for page that was renamed (#10455)
Russell Bryant committed almost 2 years ago
Fix: Build error seen on Power Architecture (#10421)
Manjul Mohan committed almost 2 years ago
[Pixtral-Large] Pixtral actually has no bias in vision-lang adapter (#10449)
Patrick von Platen committed almost 2 years ago
[BugFix] Fix hermes tool parser output error stream arguments in some cases (#10395) (#10398)
COSMOPlat committed almost 2 years ago
[CI][CPU] adding numa node number as container name suffix (#10441)
Yuan committed almost 2 years ago
[misc][plugin] improve plugin loading (#10443)
youkaichao committed almost 2 years ago
[Doc] Add the start of an arch overview page (#10368)
Russell Bryant committed almost 2 years ago
[Misc] Avoid misleading warning messages (#10438)
Jee Jee Li committed almost 2 years ago
[Bugfix] Guard for negative counter metrics to prevent crash (#10430)
Travis Johnson committed almost 2 years ago
Add openai.beta.chat.completions.parse example to structured_outputs.rst (#10433)
Michael Goin committed almost 2 years ago
[Platform][Refactor] Extract func `get_default_attn_backend` to `Platform` (#10358)
Mengqing Cao committed almost 2 years ago
[Bugfix]Fix Phi-3 BNB online quantization (#10417)
Jee Jee Li committed almost 2 years ago
[ci/build] Have dependabot ignore all patch update (#10436)
Kevin H. Luu committed almost 2 years ago
[misc] partial prefix & random input generation benchmark (#9929)
Ricky Xu committed almost 2 years ago
[ci][bugfix] fix kernel tests (#10431)
youkaichao committed almost 2 years ago
[3/N][torch.compile] consolidate custom op logging (#10399)
youkaichao committed almost 2 years ago
[Kernel] Initial Machete W4A8 support + Refactors (#9855)
Lucas Wilkinson committed almost 2 years ago
[Kernel] Explicitly specify other value in tl.load calls (#9014)
Angus Wang committed almost 2 years ago
[Hardware][XPU] AWQ/GPTQ support for xpu backend (#10107)
Yan Ma committed almost 2 years ago
[Model][Bugfix] Support TP for PixtralHF ViT (#10405)
Michael Goin committed almost 2 years ago