[Core] Move multimodal placeholder from chat utils to model definition (#20355)

Cyrus Leung committed over 1 year ago

[Docs] Replace two list with tables in intel_gaudi.md (#20414)

Michael Yao committed over 1 year ago

[doc] fix link (#20417)

Reid committed over 1 year ago

[Misc] Add rules to label Speculative Decoding Related PRs (#20406)

Lifans committed over 1 year ago

[Tests] Update online DP tests to verify that requests are balanced (#20157)

Nick Hill committed over 1 year ago

[Feature] Support MiniMax-M1 function calls features (#20297)

qscqesze committed over 1 year ago

[TPU] Add a case to cover RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8 (#20385)

QiliangCui committed over 1 year ago

[Bugfix][CI/CD][CPU] Fix CPU CI tests (#20383)

Li, Jiang committed over 1 year ago

[Misc] Small: Fix video loader return type annotations. (#20389)

Chenheli Hua committed over 1 year ago

[Bugfix] Fix import of CutlassExpertsFp8 in compressed_tensors_moe.py (#20381)

bnellnm committed over 1 year ago

Enable CPU nightly performance benchmark and its Markdown report (#18444)

Louie Tsai committed over 1 year ago

[BugFix] Fix DP headless mode arg validation (#20398)

Nick Hill committed over 1 year ago

[Bugfix] Fixes for FlashInfer's TORCH_CUDA_ARCH_LIST (#20136)

Tyler Michael Smith committed over 1 year ago

[Docs] Update EAGLE example (#20375)

Nicolò Lucchesi committed over 1 year ago

[DP] Support external DP Load Balancer mode (#19790)

Nick Hill committed over 1 year ago

[ROCm][FEAT] Enable Full Graph Mode in AITER MLA V1 Attn Backend (Decode Phase only) (#20254)

vllmellm committed over 1 year ago

[Misc] add handler HF_TOKEN is emptry string (#20369)

rongfu.leng committed over 1 year ago

[Minor] Clean up incorrect comment in test (#20382)

Nick Hill committed over 1 year ago

[V1] LogitsProcessor programming model (#16728)

afeldman-nm committed over 1 year ago

[Kernels] MoE refactor (#19636)

bnellnm committed over 1 year ago