@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, 04:30 UTC

main

[V1][VLM] Fix edge case bug for InternVL2 (#11165)

Roger Wang committed almost 2 years ago

PaliGemma 2 support (#11142)

Jani Monoses committed almost 2 years ago

[ROCm][AMD] Disable auto enabling chunked prefill on ROCm (#11146)

Gregory Shtrasberg committed almost 2 years ago

[Bugfix] Use runner_type instead of task in GritLM (#11144)

Pooya Davoodi committed almost 2 years ago

[torch.compile] Dynamic fp8 + rms_norm fusion (#10906)

Luka Govedič committed almost 2 years ago

[Misc][V1] Fix type in v1 prefix caching (#11151)

Cody Yu committed almost 2 years ago

Fix logging of the vLLM Config (#11143)

Jeremy Arnold committed almost 2 years ago

[Misc] Validate grammar and fail early (#11119)

Cody Yu committed almost 2 years ago

fix(docs): typo in helm install instructions (#11141)

Ramon Ziai committed almost 2 years ago

← Newer Page 931 of 1120 Older →