Matthias Gehre b267fe4881 [ROCm][Perf] W4A16: pad gfx11 weight and activation strides (#56301) ...

Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>

2026-10-06 08:22:33 -05:00

..

cute_dsl

[Perf][Qwen4Exp] Keep the HC up projection on the skinny GEMM path (#60027)

2026-10-05 20:09:36 +08:00

mixed_precision

[ROCm][Perf] W4A16: pad gfx11 weight and activation strides (#56301)

2026-10-06 08:22:33 -05:00

mxfp4

[Kernel] Add opt-in load-time MXFP4 dequantization (#50814)

2026-09-22 14:51:12 +08:00

mxfp6

[Feature][Humming] Humming feature integration (#56685)

2026-09-20 08:11:01 -07:00

mxfp8

[Bugfix][ROCm] Use a zero default for masked scales in the MXFP8 GEMM (#59454)

2026-10-01 11:32:25 -05:00

nvfp4

[Feature][Humming] Humming feature integration (#56685)

2026-09-20 08:11:01 -07:00

scaled_mm

[Feature][Humming] Humming feature integration (#56685)

2026-09-20 08:11:01 -07:00

__init__.py

[Bugfix][Quantization] Fix MXFP8 startup crash on layers below mm_mxfp8 shape limits (#54223)

2026-09-25 02:54:11 +00:00

base.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

zentorch_utils.py

[CPU][Zen] Route BF16 MoE inference through zentorch on AMD (#44201)

2026-08-10 23:20:05 -07:00