@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, 02:00 UTC

main

[AMD][Build] Porting dockerfiles from the ROCm/vllm fork (#11777)

Gregory Shtrasberg committed almost 2 years ago

Add quantization and guided decoding CODEOWNERS (#12228)

Michael Goin committed almost 2 years ago

[bugfix] catch xgrammar unsupported array constraints (#12210)

Cheng Kuan Yong Jason committed almost 2 years ago

[misc] add cuda runtime version to usage data (#12190)

youkaichao committed almost 2 years ago

[Misc] Update CODEOWNERS (#12229)

Roger Wang committed almost 2 years ago

[Bugfix] Fix `HfExampleModels.find_hf_info` (#12223)

Cyrus Leung committed almost 2 years ago

[Misc] Pass `attention` to impl backend (#12218)

wangxiyuan committed almost 2 years ago

[V1] Remove `_get_cache_block_size` (#12214)

Chen Zhang committed almost 2 years ago

[Model] Upgrade Aria to transformers 4.48 (#12203)

Cyrus Leung committed almost 2 years ago

[CI/Build] Make pre-commit faster (#12212)

Cyrus Leung committed almost 2 years ago

[CI/Build] Remove dummy CI steps (#12208)

Cyrus Leung committed almost 2 years ago

[misc] add placeholder format.sh (#12206)

youkaichao committed almost 2 years ago

[Model] Add Qwen2 PRM model support (#12202)

Isotr0py committed almost 2 years ago

← Newer Page 909 of 1120 Older →