@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

Aiter mha fp8 fix (#24991)

Douglas Lehr committed about 1 year ago

[Bugfix][B200] Fix `cutlass_mla` hang (#24966)

Alexander Matveev committed about 1 year ago

[gpt-oss][2] fix types for streaming (#24556)

Andrew Xia committed about 1 year ago

[Kernel] Faster pre-processing time for W4A8 (#23972)

czhu-cohere committed about 1 year ago

[Bugfix] Update import path for bc_linter_include (#24766)

Mohammad Miadh Angkad committed about 1 year ago

[V1] Logits processor docs (#22919)

afeldman-nm committed about 1 year ago

cleanup: remove adapter commons (#25045)

Simon Mo committed about 1 year ago

[V0 Deprecation] Remove V0 Core tests (#25082)

Woosuk Kwon committed about 1 year ago

[CI Bugfix] Fix failing test_invalid_env (#25078)

Michael Goin committed about 1 year ago

Remove old cutlass mla (#23961)

Matthew Bonanni committed about 1 year ago

← Newer Page 642 of 1120 Older →