huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-22 15:32:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix text-generation-server quantize (#2103)

Browse Source 
The subcommand did not work due to some broken imports.
This commit is contained in:
Daniël de Kok 2024-06-21 15:28:51 +02:00 committed by yuanwu
parent c61ef1ce85
commit f0ed8d294f
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/cli.py
View File

@ -316,7 +316,7 @@ def quantize(
logger_level=logger_level,
json_output=json_output,
)
from text_generation_server.utils.gptq.quantize import quantize
from text_generation_server.layers.gptq.quantize import quantize
quantize(
model_id=model_id,

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

@ -12,7 +12,7 @@ from huggingface_hub import HfApi
from accelerate import init_empty_weights
from text_generation_server.utils import initialize_torch_distributed, Weights
from text_generation_server.utils.hub import weight_files
from text_generation_server.utils.gptq.quant_linear import QuantLinear
from text_generation_server.layers.gptq.quant_linear import QuantLinear
from loguru import logger
from typing import Optional