Skip to content

Make SmoothQuant more General #2728

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

Merged
merged 38 commits into from
Sep 11, 2025
Merged

Make SmoothQuant more General #2728

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
38 commits
Select commit Hold shift + click to select a range
c482371
Make SmoothQuant more General
namgyu-youn Aug 11, 2025
e16edc2
refactor: use predefined ToyLinearModel
namgyu-youn Aug 11, 2025
5ec0dcf
fix incorrect parameters
namgyu-youn Aug 12, 2025
2475ad1
add type hint for dataclass
namgyu-youn Aug 12, 2025
ccb7b84
Merge branch 'main' into refactor-smoothquant
namgyu-youn Aug 15, 2025
ba89d03
use Quantization API for more generalized SmoothQuant API
namgyu-youn Aug 16, 2025
a6df6af
add PREPARE_FOR_LOADING mode for loading quantized weight
namgyu-youn Aug 19, 2025
0fc6539
update example and doc for updated SmoothQuant API
namgyu-youn Aug 19, 2025
46d5d31
remove overused/misunderstood parameters
namgyu-youn Aug 20, 2025
fc8ae4d
remove unused variable from SmoothQuant
namgyu-youn Aug 21, 2025
4f7def9
update SmoothQuant docs for user guide
namgyu-youn Aug 23, 2025
0bd922b
add benchmark comparison: base vs smoothquant
namgyu-youn Aug 26, 2025
3552a05
add benchmark: w4a8-dynamic
namgyu-youn Aug 28, 2025
4c2d55c
update docs for a4w8 benchmark
namgyu-youn Aug 28, 2025
ef9ab2c
replace Sec/Tokens with Tokens/Sec for metrics
namgyu-youn Aug 28, 2025
0d73344
update docs for SmoothQuant experiment
namgyu-youn Aug 28, 2025
6232f77
fix typo in README
namgyu-youn Aug 28, 2025
1802b5e
rename parser: repo to model
namgyu-youn Aug 28, 2025
0da2189
fix incorrect id: w4a8 -> w8a8
namgyu-youn Aug 28, 2025
7bfcf9c
remove args: precision dtype, `torch.compile`
namgyu-youn Aug 28, 2025
e571d5e
rename: precision -> precision dtype in benchmark table
namgyu-youn Aug 29, 2025
0a9ef9e
add args: bias
namgyu-youn Aug 29, 2025
62d986f
fix typo: W4A8 -> W8A8
namgyu-youn Aug 29, 2025
3f8d4ca
fix ci after adding is_bias args
namgyu-youn Aug 29, 2025
65698af
remove dead annotations in args: smoothing_factor
namgyu-youn Aug 29, 2025
d06c7ba
remove torch.compile from unittests
namgyu-youn Aug 30, 2025
ba58e89
refactor: use ToyLinearModel in AWQ
namgyu-youn Aug 30, 2025
b92caac
remove unused test case: dtype, alpha
namgyu-youn Aug 31, 2025
40b3ddb
refactor: parametrize `base_config`
namgyu-youn Sep 3, 2025
8cd2400
add TODO for future update
namgyu-youn Sep 3, 2025
50dedb8
update integration test for new SmoothQuant API
namgyu-youn Sep 3, 2025
bb25adb
add unittest: sanity check for smoothquant acc
namgyu-youn Sep 4, 2025
e630948
bugfix: ImportError for `ToyLinearModel`
namgyu-youn Sep 6, 2025
4eca4c2
revert: smoothquant unit test name
namgyu-youn Sep 7, 2025
759f86f
revert: integration test
namgyu-youn Sep 7, 2025
844a8af
update docs
namgyu-youn Sep 7, 2025
f756df9
update docs
namgyu-youn Sep 7, 2025
bd6bf13
add skiptest: no cuda case
namgyu-youn Sep 10, 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
Loading
Loading