@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 16, 04:30 UTC

main

[Pixtral] Improve loading (#11040)

Patrick von Platen committed almost 2 years ago

[Frontend] Use request id from header (#10968)

Joe Runde committed almost 2 years ago

[Bugfix] Fix usage of `deprecated` decorator (#11025)

Cyrus Leung committed almost 2 years ago

[Docs] Add dedicated tool calling page to docs (#10554)

Michael Goin committed almost 2 years ago

[V1] Do not store `None` in self.generators (#11038)

Woosuk Kwon committed almost 2 years ago

Build tpu image in release pipeline (#10936)

Richard Liu committed almost 2 years ago

[ROCm][bugfix] scpecilative decoding worker class (#11035)

Gregory Shtrasberg committed almost 2 years ago

[Neuron] Upgrade neuron to 2.20.2 (#11016)

xendo committed almost 2 years ago

[v1] fix use compile sizes (#11000)

youkaichao committed almost 2 years ago

[Misc][LoRA] Abstract PunicaWrapper (#10955)

Jee Jee Li committed almost 2 years ago

[V1] Further reduce CPU overheads in flash-attn (#10989)

Woosuk Kwon committed almost 2 years ago

[V1] Input Batch Relocation (#10962)

Varun Sundar Rabindranath committed almost 2 years ago

[Core] Require xgrammar >= 0.1.6 (#11021)

Russell Bryant committed almost 2 years ago

[V1] Fix Detokenizer loading in `AsyncLLM` (#10997)

Roger Wang committed almost 2 years ago

[torch.compile] add dynamo time tracking (#11005)

youkaichao committed almost 2 years ago

← Newer Page 934 of 1120 Older →