[BugFix] Support custom tool parsers when tool_choice is `required` and named function (#39870)

Jared Wen committed 7 months ago

[Bugfix][Core] Fix stuck chunked pipeline parallelism with async scheduling (#38726)

Jing Wang committed 7 months ago

Fix TURBOQUANT backend selection in cuda.py (#40060)

Michael Goin committed 7 months ago

Add nvfp4 support to reshape_and_cache_flash (#37332)

sychen52 committed 7 months ago

Add @bbrowning to CODEOWNERS (#40141)

Ben Browning committed 7 months ago

[Bugfix] Fix empty delta detection in Qwen3XMLToolParser streaming (#40090)

Chauncey committed 7 months ago

[CPU] Refactor CPU affinity and memory management (#39781)

Li, Jiang committed 7 months ago

[Models][Gemma4] Prevent GPU/CPU sync in `embed_input_ids` (#39234)

Lukas Geiger committed 7 months ago

[kv_offload]: Fix num CPU blocks for UniformTypeKVCacheSpecs (#39617)

Or Ozeri committed 7 months ago

[Bugfix] Add Marlin kernel in block scaled mm kernel selection. (#40105)

Maral committed 7 months ago

[Examples] Resettle Observability examples. (#40123)

wang.yuqi committed 7 months ago

[Misc] Improve new PR bot trigger condition (#40114)

Cyrus Leung committed 7 months ago

[Doc] Add Gemma 4 to supported models list (#39607)

z1ying committed 7 months ago

[CI Failure] Fix Plugin Tests (2 GPUs) Failure (#40083)

wang.yuqi committed 7 months ago

[UX] Defer some imports on CLI paths to save ~2s (#40056)

Michael Goin committed 7 months ago

[CI/Build] Apply ruff formatter to pass pre-commit (#40078)

Shinichi Hemmi committed 7 months ago

[MLA] Optimize mla indexer prepare uniform decode for MTP > 1 (#39458)

Giancarlo Delfin committed 7 months ago

[Bugfix] Temporarily disable B200 fp4 MoE layer tests (#40057)

bnellnm committed 7 months ago

Bugfix: Parakeet: `.conv.pointwise/depthwise_conv1/2.bias weigths` can exist even if `convolution_bias=False` (#40007)

Netanel Haber committed 7 months ago

[Compilation] Add Unit Tests for VllmFusionPatternMatcherPass (#39692)

BadrBasowid committed 7 months ago