@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

[VLM] Add TP support for Phi-4-MM (#14453)

Isotr0py committed over 1 year ago

[V1] TPU - Add tensor parallel support via Ray (#13618)

Alexander Matveev committed over 1 year ago

Add RLHF document (#14482)

Harry Mellor committed over 1 year ago

[Build/BugFix] Fix hopper 12.8 build (#14354)

Lucas Wilkinson committed over 1 year ago

Add training doc signposting to TRL (#14439)

Harry Mellor committed over 1 year ago

Default to `generation_config` from model (#12622)

Harry Mellor committed over 1 year ago

[Bugfix][V1] Handle MLA in kv_cache_interface (#14462)

Tyler Michael Smith committed over 1 year ago

← Newer Page 869 of 1120 Older →