@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, 09:45 UTC

main

[Misc][MacOS] fix bfloat16 error (#18249)

Reid committed over 1 year ago

[Model] Use autoweightloader for dbrx (#18251)

learner0810 committed over 1 year ago

[Misc] Add Ray Prometheus logger to V1 (#17925)

Seiji Eicher committed over 1 year ago

[doc] fix multimodal example script (#18089)

David Xia committed over 1 year ago

[Model] vLLM v1 supports Medusa (#17956)

Sky Lee committed over 1 year ago

[Build] Allow shipping PTX on a per-file basis (#18155)

Lucas Wilkinson committed over 1 year ago

[Bugfix] Fix test_eagle test (#18223)

Lucia Fang committed over 1 year ago

Adding "AMD: Tensorizer Test" to amdproduction. (#18216)

Alexei-V-Ivanov-AMD committed over 1 year ago

[Misc] Avoid cuda graph log when sizes still match (#18202)

Nicolò Lucchesi committed over 1 year ago

← Newer Page 793 of 1120 Older →