@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 17, 00:30 UTC

main

[BUGFIX] [FRONTEND] Correct chat logprobs (#5029)

Breno Faria committed over 2 years ago

[Doc]Replace deprecated flag in readme (#4526)

Ronen Schaffer committed over 2 years ago

[Core][Optimization] remove vllm-nccl (#5091)

youkaichao committed over 2 years ago

[Misc] add gpu_memory_utilization arg (#5079)

Marut Pandya committed over 2 years ago

[Docs] Add Dropbox as sponsors (#5089)

Simon Mo committed over 2 years ago

[BugFix] Fix Embedding Models with TP>1 (#5075)

Robert Shaw committed over 2 years ago

[Core] Sliding window for block manager v2 (#4545)

Michał Moskal committed over 2 years ago

← Newer Page 1049 of 1120 Older →