PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
skip quantizing mtp.fc since vLLM doesn't support (#1731)
Xin Heb3ef561dc299
diff --git a/auto_round/utils/missing_tensors.py b/auto_round/utils/missing_tensors.pyindex dd82c537b..e51f1835c 100644--- a/auto_round/utils/missing_tensors.py+++ b/auto_round/utils/missing_tensors.py@@ -497,7 +497,7 @@ def _woq_quantize_missing_tensors(target_dir: str, missing_tensors_dict: dict) -"""import re as _re- BLOCK_NAME_TO_IGNORE = ["shared_expert_gate.", "mlp.gate.", "g_proj."]+ BLOCK_NAME_TO_IGNORE = [".shared_expert_gate.", ".mlp.gate.", ".g_proj.", "mtp.fc."]qconfig = _get_woq_config_from_dir(target_dir)if qconfig is None:return missing_tensors_dict