huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-25 12:02:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix format

Browse Source 
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
This commit is contained in:
jiqing-feng 2025-02-24 16:22:34 +00:00
parent 0bad926fb8
commit a332862510
2 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
server/text_generation_server/layers/gptq/__init__.py
View File

@ -6,7 +6,12 @@ import torch
from loguru import logger from loguru import logger
from text_generation_server.utils.import_utils import SYSTEM from text_generation_server.utils.import_utils import SYSTEM
from text_generation_server.utils.log import log_once from text_generation_server.utils.log import log_once
from text_generation_server.utils.weights import Weight, Weights, WeightsLoader, UnquantizedWeight from text_generation_server.utils.weights import (
Weight,
Weights,
WeightsLoader,
UnquantizedWeight,
)
if SYSTEM == "ipex": if SYSTEM == "ipex":
from .ipex import QuantLinear from .ipex import QuantLinear
@ -181,7 +186,9 @@ class GPTQWeightsLoader(WeightsLoader):
use_exllama=use_exllama, use_exllama=use_exllama,
) )
def is_layer_skipped_quantization(self, prefix: str, modules_to_not_convert: List[str]): def is_layer_skipped_quantization(
self, prefix: str, modules_to_not_convert: List[str]
):
if modules_to_not_convert is None: if modules_to_not_convert is None:
return False 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)

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

@ -76,7 +76,9 @@ def _get_quantizer_config(model_id, revision):
quant_method = data["quantization_config"]["quant_method"] quant_method = data["quantization_config"]["quant_method"]
checkpoint_format = data["quantization_config"].get("checkpoint_format") checkpoint_format = data["quantization_config"].get("checkpoint_format")
desc_act = data["quantization_config"].get("desc_act", False) desc_act = data["quantization_config"].get("desc_act", False)
modules_to_not_convert = data["quantization_config"].get("modules_to_not_convert", None) modules_to_not_convert = data["quantization_config"].get(
"modules_to_not_convert", None
)
except Exception: except Exception:
filename = "quantize_config.json" filename = "quantize_config.json"
try: try: