[Misc] Allow `AutoWeightsLoader` to skip loading weights with specific substr in name (#18358)

Isotr0py committed over 1 year ago

[neuron] fix authorization issue (#18364)

Liangfu Chen committed over 1 year ago

fix CUDA_check redefinition in #17918 (#18287)

Lucia Fang committed over 1 year ago

Neuron up mistral (#18222)

Satyajith Chilappagari committed over 1 year ago

[Misc] Fix typo (#18330)

Gong Shufan committed over 1 year ago

Add files via uploadAdd fused MoE kernel tuning configs (fp8_w8a8) for DeepSeek V3/R1 on a single-node 8x NVIDIA H20 96GB setup (#18337)

sunyicode0012 committed over 1 year ago

[Feature]Add support for models quantized with AutoRound (#17850)

Wenhua Cheng committed over 1 year ago

[Frontend] add --quick option for vllm chat/complete (#18297)

Reid committed over 1 year ago

[Doc] Fix typo (#18355)

Elad Segal committed over 1 year ago

[Quantization] Pool model support bitsandbytes (#18087)

Jee Jee Li committed over 1 year ago

[BugFix] Fix handling of num_computed_tokens with connector (#18232)

Nick Hill committed over 1 year ago

[Doc] Move input-related docs to Features (#18353)

Cyrus Leung committed over 1 year ago

[Doc] Fix prompt embedding examples (#18350)

Li Wang committed over 1 year ago

[BugFix] [Vul] Add missing `usedforsecurity=False` in MD5 hashing to enable FIPS (#18319)

Shaoyu Yang committed over 1 year ago

fix: Add type specifications for CLI arguments in tensorizer options (#18314)

CYJiang committed over 1 year ago

[Build] Supports CUDA 12.6 and 11.8 after Blackwell Update (#18316)

Simon Mo committed over 1 year ago

[Misc] extract parser.parse_args() (#18323)

Reid committed over 1 year ago

Feature/vllm/input embedding completion api (#17590)

Nan Qin committed over 1 year ago

[Spec Decode][V0] Fix spec decode correctness test in V0 eagle/medusa (#18175)

wwl2755 committed over 1 year ago

[Doc] Add doc to explain the usage of Qwen3 thinking (#18291)

Robin committed over 1 year ago