[Docs] Reduce time spent generating API docs (#34255)

Harry Mellor committed 9 months ago

Patch protobuf for CVE-2026-0994 (#34253)

Seiji Eicher committed 9 months ago

[Frontend] Exploit tokenizers "new stream" in FastIncrementalDetokenizer (#34217)

Nick Hill committed 9 months ago

[Doc] Update Marlin support matrix for Turing (#34319)

Tianqi Ren committed 9 months ago

[Misc] Bump `fastsafetensors` version for latest fixes (#34273)

Nick Hill committed 9 months ago

[torch.compile] Enable AR+rms fusion by default available for `-O2` (#34299)

Luka Govedič committed 9 months ago

[Chore] Move `BaseRenderer` to `base.py` (#34308)

Cyrus Leung committed 9 months ago

[XPU][9/N] clean up existing ipex code/doc (#34111)

Kunshang Ji committed 9 months ago

[model] support FunASR model (#33247)

AllenDou committed 9 months ago

[CPU] Enable FP16 (Half dtype) support for s390x (#34116)

R3hankhan committed 9 months ago

[Bugfix] Fix weight naming in Qwen3.5 (#34313)

Roger Wang committed 9 months ago

[Bugfix] Fix fused MoE IMA (sans chunking) by using int64 for strides (#34279)

Tyler Michael Smith committed 9 months ago

[ModelBash][DSR1 NVFp4] Removed Bf16 Bias Cast (#34298)

Robert Shaw committed 9 months ago

Threshold fix wvSplitk for occasional CI fails (#34013)

Hashem Hashemi committed 9 months ago

[Bugfix] Fix benchmark_moe.py inplace assertion with torch >= 2.9 (#34149)

Matthias Gehre committed 9 months ago

[Plugin] Simplify IO Processor Plugin interface (#34236)

Cyrus Leung committed 9 months ago

[XPU][7/N] enable xpu fp8 moe (#34202)

zofia committed 9 months ago

[Kernel] Apply 256bit LDG/STG To Activation Kernels (#33022)

Дзержи́нский committed 9 months ago

[Bugfix][DeepSeek-V3.2] fix fp8 kvcache type cast (#33884)

Kebe committed 9 months ago

[Misc] Clean up validation logic in input processor (#34144)

Cyrus Leung committed 9 months ago