xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-09-06 10:07:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix the bug related to loading GPTP INT3 weights. (#23328)

Browse Source 
Signed-off-by: JunHowie <JunHowie@aliyun.com>
Co-authored-by: JunHowie <JunHowie@aliyun.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Jun-Howie 2025-09-01 13:39:57 +08:00 committed by GitHub
parent 8c742a66d1
commit acc1a6e10a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/layers/quantization/utils/gptq_utils.py
View File

@ -1,6 +1,7 @@
# SPDX-License-Identifier: Apache-2.0 # SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from copy import deepcopy from copy import deepcopy
from fractions import Fraction
from typing import Optional, Union from typing import Optional, Union
import regex as re import regex as re
@ -29,7 +30,7 @@ def override_config(config: QuantizationConfig, prefix: str):
if isinstance(desc_act, bool): if isinstance(desc_act, bool):
config.desc_act = desc_act config.desc_act = desc_act
config.pack_factor = 32 // config.weight_bits # packed into int32 config.pack_factor = Fraction(32, config.weight_bits) # packed into int32
if config.get_name() == "gptq_marlin": if config.get_name() == "gptq_marlin":
is_sym = get_dynamic_override(config, prefix, "sym", config.is_sym) is_sym = get_dynamic_override(config, prefix, "sym", config.is_sym)
if isinstance(is_sym, bool): if isinstance(is_sym, bool):