@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, 10:45 UTC

main

Fix failing spec decode test (#9054)

sroy745 committed about 2 years ago

[misc] add forward context for attention (#9029)

youkaichao committed about 2 years ago

[Misc] log when using default MoE config (#8971)

Divakar Verma committed about 2 years ago

[Doc] Update Granite model docs (#9025)

Nick Hill committed about 2 years ago

[Model] Adding Granite MoE. (#8206)

Shawn Tan committed about 2 years ago

[OpenVINO] Enable GPU support for OpenVINO vLLM backend (#8192)

Sergey Shlyapnikov committed about 2 years ago

[Core] CUDA Graphs for Multi-Step + Chunked-Prefill (#8645)

Varun Sundar Rabindranath committed about 2 years ago

[Misc] Update Default Image Mapper Error Log (#8977)

Alex Brooks committed about 2 years ago

[Spec Decode] (1/2) Remove batch expansion (#8839)

Lily Liu committed about 2 years ago

[Doc] Update list of supported models (#8987)

Cyrus Leung committed about 2 years ago

← Newer Page 977 of 1120 Older →