huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-29 22:12:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

More typing fixes

Browse Source
This commit is contained in:
Daniël de Kok 2025-03-06 16:48:34 +00:00
parent ed5bfe4241
commit 0a9f0dc53a
2 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/layers/gptq/__init__.py
View File

@ -188,8 +188,6 @@ class GPTQWeightsLoader(WeightsLoader):
def is_layer_skipped_quantization( def is_layer_skipped_quantization(
self, prefix: str, modules_to_not_convert: List[str] self, prefix: str, modules_to_not_convert: List[str]
): ):
if modules_to_not_convert is None:
return False
return any(module_name in prefix for module_name in modules_to_not_convert) return any(module_name in prefix for module_name in modules_to_not_convert)
def get_weights_col_packed( def get_weights_col_packed(

4
server/text_generation_server/utils/quantization.py
View File

@ -21,7 +21,7 @@ class _QuantizerConfig:
quant_method: str quant_method: str
sym: bool sym: bool
weight_block_size: Optional[List[int]] weight_block_size: Optional[List[int]]
modules_to_not_convert: Optional[List[str]] modules_to_not_convert: List[str]
@dataclass @dataclass
@ -52,7 +52,7 @@ def _get_quantizer_config(model_id, revision):
sym = False sym = False
desc_act = False desc_act = False
weight_block_size = None weight_block_size = None
modules_to_not_convert = None modules_to_not_convert = []
filename = "config.json" filename = "config.json"
try: try: