[Spec Decode] Fix offline spec_decode.py (#24257)

Ekagra Ranjan committed about 1 year ago

[Model loader]: support multi-thread model weight loading (#23928)

Yang Kaiyong committed about 1 year ago

[CI] Enable encoder model compilation test (#24442)

Jiangyun Zhu committed about 1 year ago

[Model] Remove quantized mixtral (#24437)

Jee Jee Li committed about 1 year ago

[Spec Decode][Benchmark] Add Blitzedit dataset (#23605)

Ekagra Ranjan committed about 1 year ago

[Spec Decode][Benchmark] Add Spec Bench Dataset for benchmarking (#23563)

Ekagra Ranjan committed about 1 year ago

[Model] Enable BNB support for qwen2_5_omni_thinker (#24420)

Jee Jee Li committed about 1 year ago

[Docs]add eplb_config param use docs (#24213)

rongfu.leng committed about 1 year ago

[Doc]: fix 2 hyperlinks leading to Ray site after they changed Ray's doc structure (#24438)

Didier Durand committed about 1 year ago

[Docs] Move feature compatibility tables to README (#24431)

Harry Mellor committed about 1 year ago

[Frontend] User-provided uuids for medias in chat. (RFC #22044) (#23449)

Chenheli Hua committed about 1 year ago

Move `KVEventsConfig` from `config/__init__.py` to `config/kv_events.py` (#24433)

Harry Mellor committed about 1 year ago

[Misc] Terratorch related fixes (#24337)

Christian Pinto committed about 1 year ago

[Bugfix] Fix mamba2 prefill chunking (#23279)

tomeras91 committed about 1 year ago

[Bugfix] Fix get_quant_config when using modelscope (#24421)

Li Wang committed about 1 year ago

[Doc] Fix issues in integrations/llamastack.md (#24428)

Michael Yao committed about 1 year ago

[Doc]: fix typos in Python comments (#24417)

Didier Durand committed about 1 year ago

[Docs] Fix a tip indentation and typo (#24419)

Michael Yao committed about 1 year ago

[gpt-oss][Responses API] Fix the function call id format (#24409)

Chauncey committed about 1 year ago

[Model] Remove unnecessary CUDA sync of Qwen2VL image and video preprocess (#24334)

Chatcharin Sangbutsarakum committed about 1 year ago