COMMITS
/ torchao/quantization/quant_api.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 21, 2025
V
float8tensor: small fixes for kernel_preference (#2817)
Vasiliy Kuznetsov committed
August 19, 2025
S
Add IntxUnpackedTensor (#2732)
Scott Roy committed
August 18, 2025
J
Remove group_size arg in Float8DynamicActivationInt4WeightConfig (#2779)
Jerry Zhang committed
August 15, 2025
L
Int4 sparse marlin tensor (#2771)
liangel-02 committed
August 13, 2025
L
Allow per-group quantizers in QuantOptimizer, fix state_dict (#2743)
Lisa Jin committed
J
Update Int4WeightOnlyConfig VERSION argument (#2754)
Jerry Zhang committed
A
Track API usage (#2706)
andrewor14 committed
A
Remove old `change_linear_weights_to_*` APIs (#2721)
andrewor14 committed
A
Drop support for PyTorch 2.5 and before (#2720)
andrewor14 committed
August 12, 2025
J
J
J
Align Int4Tensor implementation details with the design of Float8Tensor (#2687)
Jerry Zhang committed
August 7, 2025
J
J
Bump version for float8 dynamic quant and weight only quant configs (#2650)
Jerry Zhang committed
August 6, 2025
J
Add Float8Tensor (#2463)
Jerry Zhang committed
August 1, 2025
J
Make AWQ more general (#2400)
Jerry Zhang committed
July 26, 2025
July 17, 2025
A
Clean up QAT API surface + add separate API ref (#2567)
andrewor14 committed
July 12, 2025
J
Add support for float8 activation for Int4PreshuffledTensor (#2437)
Jerry Zhang committed
July 9, 2025
A
Fix docstrings for quantization API docs (#2471)
Apurva Jain committed
July 3, 2025
J
Remove `transpose_input` from fbgemm configs (#2422)
Jerry Zhang committed
J
Add support for Int4GroupwisePreshuffleTensor for fbgemm (#2421)
Jerry Zhang committed
June 25, 2025
X
[CPU] Enable DA8W4 on CPU (#2128)
Xia Weiwen committed
June 18, 2025
A
Fix ruff broken on main (#2404)
andrewor14 committed
Q
fix torchao quantized model in fbcode (#2396)
qizixi committed
June 13, 2025
M
Add dynamic quantization support to gemlite layout (#2327)
mobicham committed
June 10, 2025
J
Add support for bmm and `to` for fbgemm Tensor (#2337)
Jerry Zhang committed
June 5, 2025
M
Fix slicing and get_plain() in GemLite (#2288)
mobicham committed
J
Add support for fbgemm fp8 kernels (#2276)
Jerry Zhang committed
June 2, 2025
H
GPTQ updates (#2235)
HDCharles committed
May 30, 2025
E
Resolve logger warnings (#2250)
Emmanuel Ferdman committed
May 28, 2025
J
Add support for fbgemm int4 mm kernel (#2255)
Jerry Zhang committed
May 27, 2025
D
Fix Per Row scaling for inference (#2253)
Driss Guessous committed
May 24, 2025
J
Rename AOPerModuleConfig to ModuleFqnToConfig (#2243)
Jerry Zhang committed
May 21, 2025
M
Update GemLite to support vLLM V1 (#2199)
mobicham committed
Y
use correct fp8 quantization dtype for AMD GPU
Yu Guo committed
May 9, 2025
A
Set eps in end-to-end QAT flow (#2180)
andrewor14 committed
May 8, 2025
H
Enabling MOE Quantization using linear decomposition (#2043)
HDCharles committed
April 26, 2025
J
Fix AOPerModuleConfig bug in skipping quantizing modules (#2135)
Jerry Zhang committed
April 25, 2025
S
Fix numeric mismatches (#2085)
Scott Roy committed
April 24, 2025
J
Add AOPerModuleConfig (#2119)
Jerry Zhang committed
April 22, 2025
J
Update ruff version to 0.11.6 (#2103)
Jerry Zhang committed
April 15, 2025
S
Remove zero_point_domain from quant configs (#2058)
Scott Roy committed
April 14, 2025
S
Fix QDQ layout slice operation when zero_point is None (#2054)
Scott Roy committed
April 10, 2025
M
INT4 XPU enabling (#1577)
Meng, Hengyu committed
April 8, 2025
S
Move Int8DynamicActivationIntxWeightConfig out of experimental (#1968)
Scott Roy committed
S