Morph MORPH
SIGN IN SIGN UP
dhruvhead / ao UNCLAIMED
0 0 1 Python

COMMITS

/ torchao/quantization/qat/linear.py
docs
August 25, 2025
A
Add NVFP4 QAT (#2666)
andrewor14 committed
f3e549c
August 13, 2025
A
Track API usage (#2706)
andrewor14 committed
21ceb8e
A
Add float8 FakeQuantizeConfig and FakeQuantizer (#2735)
andrewor14 committed
715ea9f
A
Drop support for PyTorch 2.5 and before (#2720)
andrewor14 committed
3bad6a2
August 8, 2025
A
Generalize FakeQuantizer beyond intx (#2714)
andrewor14 committed
6cfa477
August 1, 2025
A
[bc-breaking] Generalize FakeQuantizeConfig beyond intx (#2628)
andrewor14 committed
97b090d
July 17, 2025
A
Clean up QAT API surface + add separate API ref (#2567)
andrewor14 committed
11f1a76
June 5, 2025
A
Add Float8ActInt4WeightQATQuantizer (#2289)
andrewor14 committed
0d9631b
June 2, 2025
H
GPTQ updates (#2235)
HDCharles committed
f0f1f6c
May 29, 2025
A
Enable range learning for QAT
andrewor14 committed
1b61c82
May 9, 2025
A
Set eps in end-to-end QAT flow (#2180)
andrewor14 committed
45b39b1
April 25, 2025
S
Fix numeric mismatches (#2085)
Scott Roy committed
58502e3
April 23, 2025
J
Revert D73201409 (#2105)
Jerry Zhang committed
11472c9
J
Revert "Model shapes config" (#2114)
Jerry Zhang committed
7095666
A
Model shapes config (#2036)
Apurva Jain committed
a724a37
April 22, 2025
J
Revert "Revert D73201409" (#2106)
Jerry Zhang committed
d06b3e3
J
Revert D73201409 (#2105)
Jerry Zhang committed
896f61b
J
Revert "[lint] reformat qat files" (#2104)
Jerry Zhang committed
657a00f
April 21, 2025
D
[lint] reformat qat files (#2090)
Daniel Vega-Myhre committed
10de698
N
create staticmethod for quantizing weights of QATLinear and QATEmbedding
Naveen Suda committed
4805efd
March 10, 2025
A
Add bias support for Int8DynActInt4WeightLinear (#1845)
andrewor14 committed
f64d5a1
February 21, 2025
A
Add linear bias support for QAT (#1755)
andrewor14 committed
878ec7a
January 13, 2025
A
Add convert path for quantize_ QAT API (#1540)
andrewor14 committed
f15ec15
December 16, 2024
A
Add new QAT API through quantize_ (#1415)
andrewor14 committed
200589b
November 27, 2024
Y
Add Int4CPULayout and update int4 woq (#1278)
YanbingJiang committed
719440e
November 12, 2024
A
Ruff Lint fixes (torchao/quantization) (#1244)
Apurva Jain committed
b2642fb
November 4, 2024
A
Expose FakeQuantizeConfigs in QAT quantizers (#1214)
andrewor14 committed
88d604f
October 24, 2024
A
[reland] Move QAT out of prototype (#1152)
andrewor14 committed
cf573bd