4 people fe98d90a9d [Dependency] Update Humming and remove NVFP4 scale workaround (#61556) ...

Signed-off-by: jinzhen.ljz <jinzhen.ljz@antgroup.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>

2026-10-14 13:32:36 -07:00

..

__init__.py

[Kernel] Remove AllSpark INT8 W8A16 GEMM backend (#58001)

2026-09-22 14:07:34 -07:00

conch.py

…

cpu.py

[Hardware][Power] Enable W4A16 (AWQ & GPTQ) quantization on POWER10 using VSX (#59149)

2026-09-30 19:44:48 +08:00

cutlass.py

…

dynamic_4bit.py

…

exllama.py

…

humming.py

[Dependency] Update Humming and remove NVFP4 scale workaround (#61556)

2026-10-14 13:32:36 -07:00

machete.py

…

marlin.py

…

MPLinearKernel.py

…

rdna3_w4a16.py

…

rdna_hybrid_w4a16.py

[ROCm][Perf] W4A16: speed up skinny GEMM decode, including speculative batches (#57199)

2026-10-13 17:21:30 +00:00

triton_w4a16.py

…

xpu.py

[Bugfix][XPU] Remove stale W4A8 weight after repacking (#57511)

2026-10-10 04:27:35 +00:00

zentorch.py

[CPU][Zen] Add DA8W4 (W4A8) int4 support for dense and MoE layers (#54024)

2026-10-01 15:18:25 +08:00