[Doc] Improve API docs (#18713)

Cyrus Leung committed over 1 year ago

[Bugfix]: handle hf-xet CAS error when loading Qwen3 weights in vLLM (#18701)

dylan committed over 1 year ago

[Misc] add AutoGen integration (#18712)

Reid committed over 1 year ago

[Hardware][Intel-Gaudi] [CI/Build] Add tensor parallel size = 2 test to HPU CI (#18709)

Łukasz Durejko committed over 1 year ago

[CI/Build] Split pooling and generation extended language models tests in CI (#18705)

Isotr0py committed over 1 year ago

[Model] Add support for YARN in NemotronNAS models (#18427)

Naveassaf committed over 1 year ago

[CI] fix dump_input for str type (#18697)

Ning Xie committed over 1 year ago

[CI/Build] Replace `math.isclose` with `pytest.approx` (#18703)

Cyrus Leung committed over 1 year ago

[Bugfix] Fix Mistral-format models with sliding window (#18693)

Cyrus Leung committed over 1 year ago

[Doc] Fix issue template format (#18699)

Cyrus Leung committed over 1 year ago

[GH] Add issue template for reporting CI failures (#18696)

Cyrus Leung committed over 1 year ago

[CI] add missing argument (#18694)

Ning Xie committed over 1 year ago

[Bugfix] Fix the lm_head in gpt_bigcode in lora mode (#6357)

Maximilien de Bayser committed over 1 year ago

refactor: simplify request handler, use positive condition check for handler assignment (#18690)

CYJiang committed over 1 year ago

[Misc] Fixed the abnormally high TTFT issue in the PD disaggregation example (#18644)

AlexZhao committed over 1 year ago

[CI/Build][Doc] Update `gte-Qwen2-1.5B-instruct` usage (#18683)

Cyrus Leung committed over 1 year ago

[Core][Multimodal] Convert PIL Image to array without data copy when hashing (#18682)

Lukas Geiger committed over 1 year ago

[Bugfix] Fix profiling dummy data for Pixtral (#18677)

Cyrus Leung committed over 1 year ago

[Misc] small improve (#18680)

Reid committed over 1 year ago

[CI/build] fix no regex (#18676)

Reid committed over 1 year ago