Fix unresolved-import errors when using Astral's ty by removing src.root (#35681)

Tyler Michael Smith committed 8 months ago

[Feat] Supports Anthropic Messages count_tokens API (#35588)

Chauncey committed 8 months ago

[Misc] Cleanup useless `current_platform` import (#35715)

wangxiyuan committed 8 months ago

[CPU][Distributed] Fix Enable _CPUSHMDistributed only when TP/PP ranks share the same SHM group name (#34169)

Charles Ashby committed 8 months ago

[Misc] Bound NIXL upper bound version (#35495)

Nicolò Lucchesi committed 8 months ago

[CI] Defining extended V1 e2e + engine tests (#35580)

Andreas Karatzas committed 8 months ago

[Rocm][CI] Fix LM Eval Large Models (H100) test group (#34750)

Charlie Fu committed 8 months ago

[Kernel] Integrate SM100 MXFP8 blockscaled grouped MM and quant kernels (#34448)

EdalatiAli committed 8 months ago

[ROCm][CI] Disable skinny GEMMs in language model standard tests to fix non-determinism (#35152)

Andreas Karatzas committed 8 months ago

[ROCm] add amd-quark package in requirements for rocm to use quantized models (#35658)

Hongxia Yang committed 8 months ago

[XPU] fix mxfp4 activation type (#35691)

Kunshang Ji committed 8 months ago

Fix deprecated v1 config tests (#35327)

Jesse Cai committed 8 months ago

[Attention] FA4 integration (#32974)

Lucas Wilkinson committed 8 months ago

Revert "[Bugfix] Disable TRTLLM attention with KV transfer enabled (#33192)" (#34832)

zhanqiuhu committed 8 months ago

[torch.compile] Undo the fast_moe_cold_start hack in torch>=2.11 (#35475)

Richard Zou committed 8 months ago

[Bugfix] Fix dtype mismatch in RMSNormGated.forward_native() during torch.compile (#35256)

haosdent committed 8 months ago

[Model Runner V2] Use block table apis for capture inputs (#35671)

Woosuk Kwon committed 8 months ago

fix(mxfp4): return is_monolithic=False when LoRA is enabled for Triton backend (#35382)

Seungho Yoon committed 8 months ago

[MISC] Fixing a null reference by removing parallel_utils from mypy EXCLUDE (#35630)

Taneem Ibrahim committed 8 months ago

[Mamba1] - Kernel Level Chunk Alignment for Prefix Caching (#34798)

Asaf Gardin committed 8 months ago