Netanel HaberandOpenAI Codex 70bd10930b [Quantization] Honor --linear-backend for ModelOpt W4A16 (#50273) ...

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>

2026-07-30 13:19:56 -07:00

..

cute_dsl

[Model] Add Kimi K3 support: model files and kernels [1/N] (#50089)

2026-07-29 14:10:58 +08:00

mixed_precision

[ROCm][BugFix] Triton W4A16 handling for GPTQ/AutoGPTQ qzeros layout (#47770)

2026-07-15 11:55:47 -05:00

mxfp4

[ROCm][Quark][6/N] Use MXFP4 linear kernel abstraction for aiter backend (#49348)

2026-07-27 21:35:57 -05:00

mxfp8

[ROCm][Perf] MXFP8 dense-linear + grouped-MoE GEMM optimizations for MiniMax-M3 (#46117)

2026-07-08 04:03:34 +00:00

nvfp4

[Quantization] add humming moe backend to all dense/moe oracles (#41652)

2026-07-06 13:36:07 -07:00

scaled_mm

[ROCm] Cache fp32 upcast of static e8m0 weight scale in AITER scaled_mm (#47773)

2026-07-28 11:34:16 -05:00

__init__.py

[Quantization] Honor --linear-backend for ModelOpt W4A16 (#50273)

2026-07-30 13:19:56 -07:00

base.py

Add the QuantizedActivation linear-kernel contract (#44260)

2026-06-12 13:48:15 -07:00

zentorch_utils.py

[CPU][Zen] Route W8A8 and W4A16 linear inference through zentorch on AMD Zen CPUs (#41813)

2026-05-30 14:17:21 -05:00