[USAGE] Improve error handling for weight initialization in Unquantized… (#20321)

Rafael Marcelino Koike committed about 1 year ago

Reinstate existing torch script (#24729)

Harry Mellor committed about 1 year ago

Fp8 paged attention update (#22222)

xiao-llm committed about 1 year ago

[Bugfix] Fix GLM4.1V multimodal processor with compatability for Transformers v4.56 (#24822)

Isotr0py committed about 1 year ago

[Model]: support Ling2.0 (#24627)

ant-yy committed about 1 year ago

[Misc] Fix examples openai_pooling_client.py (#24853)

wang.yuqi committed about 1 year ago

[XPU] Set consistent default KV cache layout (#24745)

Nicolò Lucchesi committed about 1 year ago

[UT] enhance free kv cache block queue popleft_n (#24220)

Ning Xie committed about 1 year ago

[P/D]`kv_output_aggregator` support P TP > D TP (#23917)

Chao Lei committed about 1 year ago

[Misc] Own KVConnectors installation (#24867)

Nicolò Lucchesi committed about 1 year ago

[Misc] rename interval to max_recent_requests (#24229)

Ning Xie committed about 1 year ago

[Doc]: fix typos in various files (#24821)

Didier Durand committed about 1 year ago

[Bugfix] MiDashengLM model contact error under concurrent testing (#24738)

bingchen-mi committed about 1 year ago

[Frontend] Skip `stop` in reasoning content (#14550)

Ce Gao committed about 1 year ago

[kv cache] update num_free_blocks in the end (#24228)

Ning Xie committed about 1 year ago

[Docs] Have a try to improve frameworks/streamlit.md (#24841)

Michael Yao committed about 1 year ago

[Hybrid Allocator] Support Pipeline Parallel (#23974)

Chen Zhang committed about 1 year ago

[Spec Decoding]Support Spec Decoding Metrics in DP Mode (#24049)

wuhang committed about 1 year ago

[Chore] Remove ipex_ops warning (#24835)

Robert Shaw committed about 1 year ago

Force use C++17 globally to avoid compilation error (#24823)

FengjinChen committed about 1 year ago