Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add gptqmodel support #2247

Merged
merged 27 commits into from
Jan 23, 2025
Merged
Changes from 1 commit
Commits
Show all changes
27 commits
Select commit Hold shift + click to select a range
a69fd22
add gptqmodel support
jiqing-feng Dec 3, 2024
3b87bae
enable gptqmodel tests
jiqing-feng Dec 4, 2024
e17c4ea
Fix Peft compat (#1)
LRL-ModelCloud Dec 5, 2024
01c7429
update gptqmodel version (#2)
ZX-ModelCloud Dec 16, 2024
c80fffd
check model has attr 'hf_device_map'
LRL-ModelCloud Jan 17, 2025
e887299
update gptqmodel version
Qubitium Jan 17, 2025
60c03af
revert test_common_gpu.py and test_gpu_examples.py
LRL-ModelCloud Jan 17, 2025
ec4d6fe
add test_gptqmodel.py
LRL-ModelCloud Jan 17, 2025
b54d034
PeftGPTQModelCommonTests require gptqmodel
LRL-ModelCloud Jan 17, 2025
12ab8a0
cleanup
LRL-ModelCloud Jan 17, 2025
c8c3d8e
use peft_model.device
LRL-ModelCloud Jan 17, 2025
946d1d7
format code
LRL-ModelCloud Jan 17, 2025
4f11d86
update copyright notice
LRL-ModelCloud Jan 17, 2025
4f13f7b
device_map is optional
LRL-ModelCloud Jan 17, 2025
9fcdd02
update Makefle, add test_gptqmodel_gpu
LRL-ModelCloud Jan 17, 2025
17440c4
Merge branch 'huggingface:main' into gptq
LRL-ModelCloud Jan 17, 2025
c206e7b
add get_gptqmodel_quant_linear to __all__
LRL-ModelCloud Jan 17, 2025
e0439fd
add gptq to quantization.md
Qubitium Jan 17, 2025
1f79dae
Update quantization.md
Qubitium Jan 17, 2025
c15a302
cleanup
LRL-ModelCloud Jan 17, 2025
6a3adc6
Merge remote-tracking branch 'origin/gptq' into gptq
LRL-ModelCloud Jan 17, 2025
59932fd
cleanup
LRL-ModelCloud Jan 17, 2025
75ddd5e
Update docs/source/developer_guides/quantization.md
Qubitium Jan 18, 2025
dab7a54
Update docs/source/developer_guides/quantization.md
Qubitium Jan 18, 2025
d5e55b6
Merge branch 'huggingface:main' into gptq
LRL-ModelCloud Jan 22, 2025
540e5af
pass device_map as a keyword argument
LRL-ModelCloud Jan 22, 2025
fa3ab05
add optimum version check for gptqmodel compatibility
LRL-ModelCloud Jan 22, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
update gptqmodel version (#2)
ZX-ModelCloud authored Dec 16, 2024
commit 01c742907d92990affc6d4fe956971a172a1e7c4
2 changes: 1 addition & 1 deletion src/peft/import_utils.py
Original file line number Diff line number Diff line change
@@ -50,7 +50,7 @@ def is_auto_gptq_available():
@lru_cache
def is_gptqmodel_available():
if importlib.util.find_spec("gptqmodel") is not None:
GPTQMODEL_MINIMUM_VERSION = packaging.version.parse("1.3.0")
GPTQMODEL_MINIMUM_VERSION = packaging.version.parse("1.4.2")
version_gptqmodel = packaging.version.parse(importlib_metadata.version("gptqmodel"))
if GPTQMODEL_MINIMUM_VERSION <= version_gptqmodel:
return True