[Bugfix] Disable sequence parallelism for Dots3 NOTE (#52172)

范裕达 committed 2 months ago

[LoRA][Gemma4] Support vision tower LoRA (#42662)

linitra24 committed 2 months ago

[Model] [Quantization] Add Ling hybrid MXFP4 routed experts support (#52114)

zexplorerhj committed 2 months ago

[Frontend] Log output token IDs at DEBUG level (#52098)

yang rui committed 2 months ago

[Misc] Add missing return type annotations in outputs.py (#52145)

Vineeta Tiwari committed 2 months ago

[XPU] Add tuned Mamba SSU configs for Intel Arc Pro B70 (#50534)

pmanczak committed 2 months ago

[Bugfix] Preserve Anthropic disable_parallel_tool_use (#52021)

Taneem Ibrahim committed 2 months ago

chore: Upstream Cohere parser fixes + tests (#51998)

JasonCohere committed 2 months ago

[Doc] Fix stale rejection_sample_method and synthetic_acceptance_rate (#51611)

QWERQWERQWE86 committed 2 months ago

fix(security): enforce audio decode duration limit in NanoNemotronVL (#50221)

Juan Pérez de Algaba committed 2 months ago

Hardware-agnostic model definition via HF transformer backend (1/N) (#49458)

Thomas Ortner committed 2 months ago

[Docs] Fix `WhisperEncoderLayer.forward` docstring in `dots3_note` (#52134)

Harry Mellor committed 2 months ago

[CI/Build][CPU] Shrink triton-cpu-build layer by dropping build artifacts (#52127)

Li, Jiang committed 2 months ago

[ROCm][Perf] Kimi-K3 Remove prefill pipeline stall in chunk KDA (#51862)

kliuae committed 2 months ago

[Feature] Mask Replay (#49577)

vx120 committed 2 months ago

Update CODEOWNERS (#52123)

Cyrus Leung committed 2 months ago

[Core] Configure custom encoder cache managers from VllmConfig (#51251)

hotTea committed 2 months ago

[Bugfix][R3] Size monolithic routing replay buffer for DP (#50874)

TomerBN-Nvidia committed 2 months ago

[CPU] Ship triton-cpu wheel and fix several hardcoded pin_memory=True (#52092)

Li, Jiang committed 2 months ago

[Model] Skip unused Jina V5 output layers (#52037)

kiroxu committed 2 months ago