@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

Support mistral interleaved attn (#9414)

Patrick von Platen committed about 2 years ago

[Core] Rename input data types (#8688)

Cyrus Leung committed about 2 years ago

[CI/Build] Test VLM embeddings (#9406)

Cyrus Leung committed about 2 years ago

[Misc] Standardize RoPE handling for Qwen2-VL (#9250)

Cyrus Leung committed about 2 years ago

[Bugfix] Molmo text-only input bug fix (#9397)

Reza Salehi committed about 2 years ago

[Bugfix][CI/Build] Fix CUDA 11.8 Build (#9386)

Lucas Wilkinson committed about 2 years ago

[Doc] Fix code formatting in spec_decode.rst (#9348)

Michael Goin committed about 2 years ago

[Frontend] Clarify model_type error messages (#9345)

Steve Grubb committed about 2 years ago

[Bugfix] Clean up some cruft in mamba.py (#9343)

Tyler Michael Smith committed about 2 years ago

← Newer Page 970 of 1120 Older →