[AutoRound] Support GLM-Image W4A16 quantization model (#3059)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
This commit is contained in:
Liang Lv authored and GitHub committed 2026-05-28 07:19:06 +00:00
1 parent 168033cac0
commit b72ffb82bb
8 files changed
+1143 -21

No files matched your search

@@ -301,10 +301,7 @@ class GlmImagePipeline(nn.Module, DiffusionPipelineProfilerMixin):
# Load transformer (DiT)
logger.info("Loading GlmImageTransformer2DModel (DiT)...")
self.transformer = GlmImageTransformer2DModel(
od_config=od_config,
quant_config=od_config.quantization_config,
)
self.transformer = GlmImageTransformer2DModel(od_config=od_config, quant_config=od_config.quantization_config)
# Weight sources for DiT loading
self.weights_sources = [