@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 14, 05:30 UTC

main

Support mnnvl all2allv from Flashinfer (#21003)

Shu Wang committed about 1 year ago

[Misc] Improve type annotations for jsontree (#25577)

Cyrus Leung committed about 1 year ago

[Bug] fix import and unit test (#25558)

Jonas M. Kübler committed about 1 year ago

[misc] update the warning message (#25566)

youkaichao committed about 1 year ago

[BugFix] Potential Fix for FA3 full-cudagraph IMA (#25490)

Lucas Wilkinson committed about 1 year ago

[CI/Build] Fix v1 OOT registration test (#25547)

Isotr0py committed about 1 year ago

← Newer Page 628 of 1120 Older →