[4/N] Quantization Refactor: AWQ schemes and Kernel call and weight init split (#21126)

2026-04-30 14:51:01 +03:00
parent b1ef99f65f
commit 577dbc4ab9
20 changed files with 1421 additions and 1033 deletions
@@ -12,7 +12,7 @@ import unittest

 import torch

-from sglang.srt.layers.quantization.awq_triton import (
+from sglang.srt.layers.quantization.awq.awq_triton import (
    AWQ_TRITON_SUPPORTED_GROUP_SIZES,
    awq_dequantize_triton,
    awq_gemm_triton,