COMMITS
/ torchao/quantization/__init__.py August 27, 2025
S
X
[CPU] Introduce Int4OpaqueTensor to replace Int4CPULayout in AQT (#2798)
Xia Weiwen committed
August 26, 2025
S
Update IntxUnpackedTensor to support dynamic activation (#2861)
Scott Roy committed
August 19, 2025
S
Add IntxUnpackedTensor (#2732)
Scott Roy committed
August 15, 2025
L
Int4 sparse marlin tensor (#2771)
liangel-02 committed
August 12, 2025
August 7, 2025
August 6, 2025
J
Add Float8Tensor (#2463)
Jerry Zhang committed
July 12, 2025
J
Add support for float8 activation for Int4PreshuffledTensor (#2437)
Jerry Zhang committed
July 3, 2025
J
Add support for Int4GroupwisePreshuffleTensor for fbgemm (#2421)
Jerry Zhang committed
June 18, 2025
A
[BE] Convert quant_primitives methods private (#2350)
Apurva Jain committed
June 2, 2025
H
GPTQ updates (#2235)
HDCharles committed
May 31, 2025
J
Add back AOPerModuleConfig for BC (#2282)
Jerry Zhang committed
May 28, 2025
J
Add support for fbgemm int4 mm kernel (#2255)
Jerry Zhang committed
May 24, 2025
J
Rename AOPerModuleConfig to ModuleFqnToConfig (#2243)
Jerry Zhang committed
May 21, 2025
A
Remove preserve_zero and zero_point_domain from choose_qparams_affine (#2149)
Apurva Jain committed
May 14, 2025
S
Update __init__.py (#2206)
Scott Roy committed
April 26, 2025
J
Fix AOPerModuleConfig bug in skipping quantizing modules (#2135)
Jerry Zhang committed
J
Add AOPerModuleConfig to `torchao.quantization` (#2134)
Jerry Zhang committed
March 17, 2025
A
Add copyright header and pre-commit validator (#1900)
Apurva Jain committed
March 14, 2025
D
Config Serilization No Deps (#1875)
Driss Guessous committed
March 13, 2025
A
Add CUTLASS-based row-wise scaled sparse FP8 kernel (#1671)
Aleksandar Samardžić committed
February 14, 2025
V
config migration: fpx, gemlite, uintx (#1697)
Vasiliy Kuznetsov committed
V
config migration: int* (#1696)
Vasiliy Kuznetsov committed
V
config migration: float8* (#1694)
Vasiliy Kuznetsov committed
V
[bc-breaking] enable direct configuration in quantize_ (#1595)
Vasiliy Kuznetsov committed
February 5, 2025
T
Add CUTLASS-based W4A4 (#1515)
Thien Tran committed
December 20, 2024
J
Add gemlite kernel option to autoquant (#1449)
Jerry Zhang committed
December 16, 2024
H
gemlite integration in torchao (#1034)
HDCharles committed
A
Add new QAT API through quantize_ (#1415)
andrewor14 committed
December 11, 2024
J
Add marlin and semi sparse + quant option to autoquant (#1399)
Jerry Zhang committed
J
Add exhaustive config option to intmm kernel (#1392)
Jerry Zhang committed
November 27, 2024
J
Add floating point options for autoquant and add accuracy measurement (#1355)
Jerry Zhang committed
November 13, 2024
J
Update torchao api reference and add contributor guide (#1255)
Jerry Zhang committed
November 12, 2024
A
Ruff Lint fixes (torchao/quantization) (#1244)
Apurva Jain committed
October 15, 2024
A
Add generic fake quantized linear for QAT (#1020)
andrewor14 committed
October 2, 2024
A
Add float8_static_activation_float8_weight to user-facing API (#994)
Apurva Jain committed
J
Add example for awq like flow (#990)
Jerry Zhang committed
A
Float8 dynamic autoquant (#946)
Apurva Jain committed
September 5, 2024
H
int4 fixes and improvements (#804)
HDCharles committed
September 4, 2024
J
Add more information to quantized linear module and added some logs (#782)
Jerry Zhang committed
August 30, 2024
D
Add Float8 Weight Only and FP8 weight + dynamic activation (#740)
Driss Guessous committed
August 29, 2024
J
[reland] Refactor quant_llm to work with affine quantized tensor (#696) (#772)
Jerry Zhang committed
August 28, 2024
J
Revert "Refactor quant_llm to work with affine quantized tensor" (#767)
Jerry Zhang committed
J
Refactor quant_llm to work with affine quantized tensor (#696)
Jerry Zhang committed
July 26, 2024
J
Refactor LinearActQuantizedTensor (#542)
Jerry Zhang committed
J
Implement sparsity as a AQT Layout (#498)
Jesse Cai committed
July 4, 2024
J
Renaming `quantize` to `quantize_` (#467)
Jerry Zhang committed
June 22, 2024
J
Add doc page to README.md (#367)
Jerry Zhang committed
June 21, 2024
H
eval script fixes (#414)
HDCharles committed