forward fix PR 14245, restore build on ROCm 6.2 (#14709)

Jeff Daily committed over 1 year ago

[V1] TPU - Enable prefix caching by default (#14773)

Alexander Matveev committed over 1 year ago

[Doc] Fix small typo in Transformers fallback (#14791)

Chen Zhang committed over 1 year ago

[Doc] Fix typo in documentation (#14783)

yasu52 committed over 1 year ago

[Attention] Remove slow setattr in MLA (#14769)

Lucas Wilkinson committed over 1 year ago

[V1] Detokenizer: Respect Stop Tokens + not include_stop_str_in_output (#14624)

afeldman-nm committed over 1 year ago

[V1][Core] using cached vocab_size for Structured Outputs (#14630)

Aaron Pham committed over 1 year ago

[Misc] Clean up processor tests (#14771)

Cyrus Leung committed over 1 year ago

[V1][Minor] Minor enhancements on scheduler (#14732)

Woosuk Kwon committed over 1 year ago

[Bugfix] Fix prompt format of GLM4V (#14539)

Cyrus Leung committed over 1 year ago

[VLM] Support loading InternVideo2.5 models as original InternVLChatModel (#14738)

Isotr0py committed over 1 year ago

[VLM] Support pan-and-scan for Gemma3 multi-modal processor (#14672)

Cyrus Leung committed over 1 year ago

[Bugfix] fix benchmark moe (#14653)

Jee Jee Li committed over 1 year ago

[CI/Build] Delete ultravox LoRA test (#14730)

Jee Jee Li committed over 1 year ago

[Bugfix] Fix chunked prefill for GGUF (#14666)

Szymon Ożóg committed over 1 year ago

[Quant] Bamba SupportsQuant (#14698)

Kyle Sayers committed over 1 year ago

[Quant] BartModel SupportsQuant (#14699)

Kyle Sayers committed over 1 year ago

[V1][TPU] Add assertion on multi-step-scheduler (#14707)

Siyuan Liu committed over 1 year ago

[Config][Disaggregated] Add timeout configuration for the torch.store and add KVTransferConfig.kv_connector_extra_config (#14367)

Mathis Felardos committed over 1 year ago

[BugFix][TritonMLA] Process weights after model loading for GGUF (#14555)

TY-AMD committed over 1 year ago