fix(quantization): Fix AWQ dequantize on Intel XPU and refactor AutoAWQ config (#42727)

Signed-off-by: Alex <alex.tech.lab@outlook.com>
Signed-off-by: AlexHuang <jihuihuang@tencent.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
AlexHuang
2026-06-18 20:12:28 +08:00
committed by GitHub
co-authored by Claude Kunshang Ji mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 351c72d6e5
commit 8d4f54966c
20 changed files with 580 additions and 429 deletions
@@ -175,7 +175,7 @@ class CPUWNA16LinearKernel(MPLinearKernel):
and torch.cpu._is_amx_tile_supported()
)
# layer.use_w4a8 = False
# AWQ format will be converted to GPTQ format in `AWQMarlinLinearMethod`
# AWQ format will be converted to GPTQ format in `AutoAWQMarlinLinearMethod`
if layer.use_w4a8:
self._process_gptq_weights_w4a8(layer)
else: