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.

Sign up for GitHub

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

[Feature] Add GPTQ and uniform interfaces #538

Merged
merged 26 commits into from
May 24, 2023
Merged

[Feature] Add GPTQ and uniform interfaces #538

Changes from 1 commit
Commits
Show all changes
26 commits
Select commit Hold shift + click to select a range
d0569a0
add gptq implementation
May 4, 2023
89a8abd
pre-checkout
May 6, 2023
4c74165
passed resnet example
May 6, 2023
6f536b9
passed llama example
May 10, 2023
7cd6c16
aglin gptq acc
May 12, 2023
26b99bf
add activation quantization
May 17, 2023
a7a35de
uniform interfaces
May 17, 2023
2df570b
add gptq readme
May 17, 2023
203a5e8
update mmrazor_large redame
May 17, 2023
05597cb
add gptq opt example
May 17, 2023
77eb412
fix sparse_gpt example for opt
May 18, 2023
b14c4fc
fix import Protocol from py37
May 19, 2023
86da5b3
fix error function name
May 19, 2023
3825e04
fix bug in test
May 19, 2023
d636a79
fix bug
May 19, 2023
1a29bf2
fix bug
May 19, 2023
791dd7c
limit sparsegpt test with torch>=1.12
May 19, 2023
e4203ee
add docstring for gptq and sparse_gpt
May 19, 2023
daacadc
pre-commit
May 19, 2023
f71040e
align acc & add save load ckpt & add ut
May 23, 2023
f70ade9
fix ut
May 24, 2023
035bfbb
fix ut
May 24, 2023
c7e05f7
fix ut
May 24, 2023
4c99385
fix ut & add torch2.0 for ci
May 24, 2023
521696e
del torch2.0 for ci
May 24, 2023
cb1e466
fix ut
May 24, 2023
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
limit sparsegpt test with torch>=1.12
  • Loading branch information
FIRST_NAME LAST_NAME authored and FIRST_NAME LAST_NAME committed May 19, 2023
commit 791dd7c7669230e3c34a65f3ebed2c8827c0cbfc
5 changes: 5 additions & 0 deletions tests/test_impl/test_pruning/test_sparse_gpt/test_op.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,13 +4,16 @@
import torch
import torch.nn as nn

from mmrazor import digit_version
from mmrazor.implementations.pruning import sparse_gpt


class TestSparseGptOps(unittest.TestCase):

@torch.no_grad()
def test_op(self):
if digit_version(torch.__version__) < digit_version('1.12.0'):
self.skipTest('torch<1.12.0')

def get_loss(linear, linear1, data):
y = linear(data)
Expand Down Expand Up @@ -53,6 +56,8 @@ def infer(model, dataset):

@torch.no_grad()
def test_model(self):
if digit_version(torch.__version__) < digit_version('1.12.0'):
self.skipTest('torch<1.12.0')
import torchvision
model = torchvision.models.resnet18()

Expand Down