Fix `validate-config` pre-commit check (#25157)

Harry Mellor committed about 1 year ago

Fix forward reference warning in documentation (#25150)

Harry Mellor committed about 1 year ago

[Docs] add the parallel sampling usage in LLMEngine and AsyncLLM (#24222)

William Song committed about 1 year ago

[Docs] Fix pooling-params doc references in openai_compatible_server.md (#24939)

Kay Yan committed about 1 year ago

Move `StructuredOutputsConfig` from `config/__init__.py` to `config/structured_outputs.py` (#25153)

Harry Mellor committed about 1 year ago

[Model] Improve Pooling Model (#25149)

Jee Jee Li committed about 1 year ago

[Frontend] Support setting logprobs to -1 (#25031)

Chauncey committed about 1 year ago

silu-v1: Fix EPS not being used during max-reduction (#25069)

Elvir Crnčević committed about 1 year ago

Fix: Add explicit #include <omp.h> for OpenMP compatibility on certain toolchains (#24951)

ihb2032 committed about 1 year ago

[Chore] Cleanup guided namespace, move to structured outputs config (#22772)

Aaron Pham committed about 1 year ago

[Doc] Fix cross-reference warnings (#25058)

Punitvara committed about 1 year ago

Add 'path' option to ImagePrompt data_format (#25081)

Gerard Finol committed about 1 year ago

[Qwen] Add fp8 checkpoint support for qwen3-next. (#25079)

Tao He committed about 1 year ago

[Bugfix] when use s3 model cannot use default load_format (#24435)

rongfu.leng committed about 1 year ago

Retrieve `sliding_window` from text config in Gemma3 MM (#25085)

Harry Mellor committed about 1 year ago

[Docs] Fix API Reference (#25140)

Harry Mellor committed about 1 year ago

[Kernel] Better inf handling for grouped topk cu (#24886)

Lumina committed about 1 year ago

[CLI] Use streaming in CLI chat and completion commands (#23769)

Simon Mo committed about 1 year ago

[benchmark] add peak throughput metrics and plot (#23867)

Simon Mo committed about 1 year ago

[Spec Decode] Efficient padded speculation (#24539)

Benjamin Chislett committed about 1 year ago