@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, 19:45 UTC

main

[Bugfix] Wrong requirements path - rocm (#14527)

Martin Hoyer committed over 1 year ago

[Attention] Default to FlashMLA backend for MLA (#14451)

Lucas Wilkinson committed over 1 year ago

[V1] Support bad_words in sampler (#13376)

22quinn committed over 1 year ago

Update CODEOWNERS for structured output (#14496)

Russell Bryant committed over 1 year ago

[Bugfix] DeepSeek Accuracy (#14476)

Lucas Wilkinson committed over 1 year ago

Move requirements into their own directory (#12547)

Harry Mellor committed over 1 year ago

← Newer Page 868 of 1120 Older →