COMMITS
/ test/quantization/test_quant_primitives.py August 13, 2025
A
Drop support for PyTorch 2.5 and before (#2720)
andrewor14 committed
July 24, 2025
A
[BE] Convert quantization internal methods private (#2568)
Apurva Jain committed
June 18, 2025
A
[BE] Convert quant_primitives methods private (#2350)
Apurva Jain committed
May 30, 2025
X
Enable AWQ on Intel GPU. (#2248)
XiaoWang committed
May 21, 2025
A
Remove preserve_zero and zero_point_domain from choose_qparams_affine (#2149)
Apurva Jain committed
April 10, 2025
M
INT4 XPU enabling (#1577)
Meng, Hengyu committed
January 29, 2025
S
Consolidate `ZeroPointDomain.NONE` & `None` zero point domains (#1556)
sanchitintel committed
January 25, 2025
D
add separate quantization primitives for float8 (#1597)
Daniel Vega-Myhre committed
December 17, 2024
M
Expose zero_point_domain as arguments (#1401)
Meng, Hengyu committed
December 2, 2024
A
Lint fixes test/quantization (#1359)
Apurva Jain committed
November 27, 2024
Y
Add Int4CPULayout and update int4 woq (#1278)
YanbingJiang committed
October 4, 2024
J
Unskip `test_choose_qparams_token_asym` in 2.6 (#1004)
Jerry Zhang committed
September 30, 2024
M
Skip test_choose_qparams_token_asym on pt 2.6 (#981)
Mark Saroufim committed
September 7, 2024
M
Update the way scale is calculated for affine Symmetric (#805)
Mengtao Yuan committed
August 14, 2024
M
retry version guard fix (#679)
Mark Saroufim committed
July 29, 2024
Y
Fix int4pack_mm error (#517)
YanbingJiang committed
July 17, 2024
A
Add cachemask variant for fake_quantize_affine (#500)
andrewor14 committed
July 11, 2024
A
Add general fake_quantize_affine op (#492)
andrewor14 committed
June 12, 2024
V
make torchao test discovery pass in fbcode
Vasiliy Kuznetsov committed
June 9, 2024
J
Move quant ops to utils.py (#331)
Jerry Zhang committed
June 7, 2024
J
Move some util functions from quantization.utils to torchao.utils (#337)
Jerry Zhang committed
June 5, 2024
J
Refactor rest of tinygemm quant primitive ops (#321)
Jerry Zhang committed
June 3, 2024
C
Check dequantize_affine is idempotent (#309)
cpuhrsch committed
May 18, 2024
J
Fix quant_primitive dtype that caused perf regression (#253)
Jerry Zhang committed
May 15, 2024
A
Fix CI after quantize op change in PyTorch core (#244)
andrewor14 committed
May 14, 2024
J
Enable dispatch to tinygemm int4 and int8 kernels for quantized tensor (#230)
Jerry Zhang committed
May 9, 2024
J
Add more options in choose_qparams_affine for tinygemm op (#227)
Jerry Zhang committed
May 8, 2024
J
Some follow up fixes for quant primitives (#220)
Jerry Zhang committed
May 3, 2024
J
`quantize_activation_per_token_absmax` use general quant primitives (#193)
Jerry Zhang committed
J
Reduce memory usage for symmetric choose_qparams (#210)
Jerry Zhang committed
J
quant primitives: always set min val for scale (#201)
Jerry Zhang committed
April 29, 2024
J
deduplicate code for some torchao q/dq ops (#173)
Jerry Zhang committed
April 24, 2024
J
[quant] Add per block quantization primitives (#159)
Jerry Zhang committed
April 18, 2024
A
Initial support for 8da4w QAT (#138)
andrewor14 committed
April 1, 2024
A
[test] `get_group_qparams_symmetric` matches observer (#94)
andrewor14 committed