test_attention compat with coming xformers change (#20487)

Jeremy Reizenstein committed over 1 year ago

[Misc] remove unused import (#20517)

Reid committed over 1 year ago

[Misc] Add logger.exception for TPU information collection failures (#20510)

Reid committed over 1 year ago

[v1] Re-add fp32 support to v1 engine through FlexAttention (#19754)

Isotr0py committed over 1 year ago

Fix unknown attribute of topk_indices_dtype in CompressedTensorsW8A8Fp8MoECutlassMethod (#20507)

Lucia Fang committed over 1 year ago

[Misc] Remove the unused LoRA test code (#20494)

Jee Jee Li committed over 1 year ago

[doc] small fix (#20506)

Reid committed over 1 year ago

[Misc] Add security warning for development mode endpoints (#20508)

Reid committed over 1 year ago

[Doc] fix mutltimodal_inputs.md gh examples link (#20497)

Guy Stone committed over 1 year ago

[CI Bugfix] Fix pre-commit failures on main (#20502)

Michael Goin committed over 1 year ago

[feat]: CUTLASS block scaled group gemm for SM100 (#19757)

Duncan Moss committed over 1 year ago

Enable V1 for Hybrid SSM/Attention Models (#20016)

Thomas Parnell committed over 1 year ago

[Misc] Small: Remove global media connector. Each test should have its own test connector object. (#20395)

Chenheli Hua committed over 1 year ago

[CI] add kvcache-connector dependency definition and add into CI build (#18193)

Peter Pan committed over 1 year ago

[Doc] Fix classification table in list of supported models (#20489)

Cyrus Leung committed over 1 year ago

[Model][3/N] Automatic conversion of CrossEncoding model (#20168)

wang.yuqi committed over 1 year ago

[Bug][Frontend] Fix structure of transcription's decoder_prompt (#18809)

sangbumlikeagod committed over 1 year ago

Support Llama 4 for fused_marlin_moe (#20457)

Michael Goin committed over 1 year ago

[Misc] Add SPDX-FileCopyrightText (#20428)

Jee Jee Li committed over 1 year ago

[Perf] Optimize Vectorization Utils for Int 8 Quantization Kernels (#20331)

Wentao Ye committed over 1 year ago