@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, 23:15 UTC

main

[ci] Use sccache to build images (#5419)

Kevin H. Luu committed over 2 years ago

[Doc] Update debug docs (#5438)

Cyrus Leung committed over 2 years ago

[misc] add hint for AttributeError (#5462)

youkaichao committed over 2 years ago

[Bugfix] TYPE_CHECKING for MultiModalData (#5444)

Arthur Kim committed over 2 years ago

[Kernel] Vectorized FP8 quantize kernel (#5396)

Cody Yu committed over 2 years ago

[Bugfix] Add device assertion to TorchSDPA (#5402)

Li, Jiang committed over 2 years ago

[Hardware] Initial TPU integration (#5292)

Woosuk Kwon committed over 2 years ago

[CI] Upgrade codespell version. (#5381)

SangBin Cho committed over 2 years ago

[Doc] add common case for long waiting time (#5430)

youkaichao committed over 2 years ago

[Core][Distributed] add same-node detection (#5369)

youkaichao committed over 2 years ago

[Frontend] Customizable RoPE theta (#5197)

sasha0552 committed over 2 years ago

← Newer Page 1042 of 1120 Older →