@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

Handle triton kernel import exception (#25319)

Ming Yang committed about 1 year ago

[Model] Enable DP for ViT in Qwen2-VL (#25445)

Cyrus Leung committed about 1 year ago

[DP/EP][GPTOSS] Use triton matmul-ogs kernels for GPTOSS DP/EP (#24588)

Varun Sundar Rabindranath committed about 1 year ago

[Docs] Fix griffe warnings in vllm/lora/ops (#25369)

Michael Yao committed about 1 year ago

[XPU] Fix `compile_size` is `None` case. (#25433)

Kunshang Ji committed about 1 year ago

[feat] Support MRoPE + YaRN (#25384)

JJJYmmm committed about 1 year ago

[Bug] Fix Long Context OOM Issue (#25290)

Wentao Ye committed about 1 year ago

[BugFix] [DP/EP] Fix slow execution when BS <= DP (#25407)

Matthew Bonanni committed about 1 year ago

[Bugfix] Fix missing `clear_connector_metadata` (#25397)

Nicolò Lucchesi committed about 1 year ago

← Newer Page 632 of 1120 Older →