[Frontend] deprecate `--device` arg (#18399)

Kebe committed over 1 year ago

[Misc] MultiConnector._connectors type (#18423)

Nicolò Lucchesi committed over 1 year ago

[Bugfix][Failing Test] Fix nixl connector test when promt size < block size (#18429)

wwl2755 committed over 1 year ago

Revert "[Bugfix] Fix MRoPE Errors in the Qwen-VL Model When Processing Pure Text (#18407)" (#18456)

Cyrus Leung committed over 1 year ago

[Bug] Fix moe_sum signature (#18440)

bnellnm committed over 1 year ago

[Bugfix] config.head_dim is now explicitly set to None (#18432)

Gregory Shtrasberg committed over 1 year ago

[TPU] Re-enable the Pallas MoE kernel (#18025)

Michael Goin committed over 1 year ago

fix:Build torch wheel inline rather than picking from nightly (#18351)

Dilip Gowda Bhagavan committed over 1 year ago

[Kernel] update comment for KV shape in unified triton attn (#18099)

Percy committed over 1 year ago

[Model] use AutoWeightsLoader for bloom (#18300)

Calvin Chen committed over 1 year ago

[Minor] Rename quantization nvfp4 to modelopt_fp4 (#18356)

Michael Goin committed over 1 year ago

[Misc] refactor prompt embedding examples (#18405)

Reid committed over 1 year ago

[Bugfix] Fix MRoPE Errors in the Qwen-VL Model When Processing Pure Text (#18407)

燃 committed over 1 year ago

[CI] Add mteb testing to test the accuracy of the embedding model (#17175)

wang.yuqi committed over 1 year ago

Update cpu.txt (#18398)

汪志鹏 committed over 1 year ago

[Misc] Add LoRA code owner (#18387)

Jee Jee Li committed over 1 year ago

[doc] update env variable export (#18391)

Reid committed over 1 year ago

[Bugfix] fix adding bias twice in ipex GPTQ quantization (#18363)

Random Fly committed over 1 year ago

[release] Change dockerhub username for TPU release (#18389)

Kevin H. Luu committed over 1 year ago

[Core] [Bugfix]: tensor parallel with prompt embeds (#18171)

Nan Qin committed over 1 year ago