[Refactor] Rename commnication utils (#20091)

Wentao Ye committed over 1 year ago

[TPU] add kv cache update kernel (#19928)

Chengji Yao committed over 1 year ago

[Hardware][Intel GPU] Add v1 Intel GPU support with Flash attention backend. (#19560)

Kunshang Ji committed over 1 year ago

Spam folks if config.py changes (#20131)

Tyler Michael Smith committed over 1 year ago

[Doc] Rename page titles (#20130)

Cyrus Leung committed over 1 year ago

[Doc] Auto sign-off for VSCode (#20132)

Cyrus Leung committed over 1 year ago

[Doc] Automatically signed-off by PyCharm (#20120)

wang.yuqi committed over 1 year ago

[Bug Fix] Fix address/port already in use error for deep_ep test (#20094)

Wentao Ye committed over 1 year ago

Revert "[Bugfix] default set cuda_graph_sizes to max_num_seqs for v1 engine" (#20128)

Michael Goin committed over 1 year ago

[Bugfix][V1][ROCm] Fix AITER Flash Attention Backend (Fix API Break and Local Attention Logic: affecting Llama4) (#19904)

TJian committed over 1 year ago

[Docs] Improve frameworks/helm.md (#20113)

Michael Yao committed over 1 year ago

[Misc] Use collapsible blocks for benchmark examples. (#20017)

Reid committed over 1 year ago

[CPU] Fix torch version in x86 CPU backend (#19258)

Li, Jiang committed over 1 year ago

[Refactor] Remove unused library (#20099)

Wentao Ye committed over 1 year ago

[Doc] Update docs for New Model Implementation (#20115)

Cyrus Leung committed over 1 year ago

[Bugfix] Allow `CUDA_VISIBLE_DEVICES=''` in `Platform.device_id_to_physical_device_id` (#18979)

Seiji Eicher committed over 1 year ago

[Benchmark][Bug] Fix multiple bugs in bench and add args to spec_decode offline (#20083)

Ekagra Ranjan committed over 1 year ago

[PD] Skip `tp_size` exchange with rank0 (#19413)

Nicolò Lucchesi committed over 1 year ago

[Bugfix] Fix Mistral tool-parser regex for nested JSON (#20093)

Michael Goin committed over 1 year ago

[CI] Add SM120 to the Dockerfile (#19794)

Michael Goin committed over 1 year ago