@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only
Fork 0

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, 11:00 UTC

main

[Misc] Fix ScalarType float4 naming (#17690)

Lucas Wilkinson committed over 1 year ago

[Doc] Update notes for H2O-VL and Gemma3 (#17219)

Cyrus Leung committed over 1 year ago

[Bugfix] Fixed prompt length for random dataset (#17408)

Mikhail Podvitskii committed over 1 year ago

[Model] Add GraniteMoeHybrid 4.0 model (#17497)

Stan Wozniak committed over 1 year ago

[Bugfix] LoRA - Retire unused maxnreg LoRA kernel argument (#17677)

Varun Sundar Rabindranath committed over 1 year ago

[TPU][V1] Add support for top-logprobs (#17072)

Nicolò Lucchesi committed over 1 year ago

Use git-path commit in hook (#17616)

Thomas J. Fan committed over 1 year ago

[Build/CI] Upgrade CUTLASS to 3.9.2 (#17641)

Tyler Michael Smith committed over 1 year ago

← Newer Page 806 of 1120 Older →