Fix: Spelling of inference (#17387)

a2q1p committed over 1 year ago

Transformers backend tweaks (#17365)

Harry Mellor committed over 1 year ago

[Frontend] Support `chat_template_kwargs` in `LLM.chat` (#17356)

Cyrus Leung committed over 1 year ago

`pre-commit autoupdate` (#17380)

Harry Mellor committed over 1 year ago

[Bugfix] Clean up MiniMax-VL and fix processing (#17354)

Cyrus Leung committed over 1 year ago

[Doc] Fix QWen3MOE info (#17381)

Jee Jee Li committed over 1 year ago

Update docs requirements (#17379)

Harry Mellor committed over 1 year ago

[Model] Ignore rotary embed load for Cohere model (#17319)

Ekagra Ranjan committed over 1 year ago

[Build][Bugfix] Restrict setuptools version to <80 (#17320)

Gregory Shtrasberg committed over 1 year ago

[Fix] Documentation spacing in compilation config help text (#17342)

Hyogeun Oh (오효근) committed over 1 year ago

[Misc]Use a platform independent interface to obtain the device attributes (#17100)

ponix-j committed over 1 year ago

[Misc] Move config fields to MultiModalConfig (#17343)

Cyrus Leung committed over 1 year ago

[Model] support MiniMax-VL-01 model (#16328)

qscqesze committed over 1 year ago

[Misc] Add a Jinja template to support Mistral3 function calling (#17195)

Chauncey committed over 1 year ago

[Bugfix] Add contiguous call inside rope kernel wrapper (#17091)

Zhengyuan Su (苏政渊) committed over 1 year ago

Ignore `'<string>'` filepath (#17330)

Richard Zou committed over 1 year ago

[Bugfix] Fix `numel()` downcast in fused_layernorm_dynamic_per_token_quant.cu (#17316)

Richard Barnes committed over 1 year ago

[model] make llama4 compatible with pure dense layers (#17315)

Lucia Fang committed over 1 year ago

[V1][Spec Decode] Make Eagle model arch config driven (#17323)

Ekagra Ranjan committed over 1 year ago

implement Structural Tag with Guidance backend (#17333)

Michał Moskal committed over 1 year ago