[NPU] [Quantization] w4a4 MoE layer support (#18924)

2026-03-11 16:52:35 +03:00
parent 9991debde3
commit ed42af99a9
7 changed files with 342 additions and 2 deletions
@@ -6,6 +6,7 @@ To load already quantized models, simply load the model weights and config. Agai
 - [x] W4A4 dynamic linear
 - [x] W8A8 static linear
 - [x] W8A8 dynamic linear
+- [x] W4A4 dynamic MOE
 - [x] W4A8 dynamic MOE
 - [x] W8A8 dynamic MOE