apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Revert "【New Feature】W4afp8 supports per group quantization (#4272)" (#4854)

Browse Source 
This reverts commit 93fcf7e4ec.
This commit is contained in:
YuBaoku
2025-11-06 17:48:28 +08:00
committed by GitHub
parent 3478d20262
commit 819b2dbbae
26 changed files with 1718 additions and 4378 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
fastdeploy/model_executor/layers/quantization/mix_quant.py
View File

@@ -39,7 +39,6 @@ class MixQuantConfig(QuantConfigBase):
is_permuted: bool = True,
is_quantized: bool = False,
hadamard_block_size: int = 128,
moe_dynamic_quant: bool = False,
) -> None:
super().__init__()
self.dense_quant_type = dense_quant_type
@@ -58,7 +57,6 @@ class MixQuantConfig(QuantConfigBase):
self.is_checkpoint_bf16 = not is_quantized
self.is_quantized = is_quantized
self.hadamard_block_size = hadamard_block_size
self.moe_dynamic_quant = moe_dynamic_quant
def name(self) -> str:
return "mix_quant"
@@ -75,7 +73,6 @@ class MixQuantConfig(QuantConfigBase):
config.get("is_permuted", True),
config.get("is_quantized", False),
config.get("hadamard_block_size", 128),
config.get("moe_dynamic_quant", False),
)
def get_quant_method(self, layer) -> Optional[QuantMethodBase]: