COMMITS
/ torchao/quantization/qat/utils.py August 13, 2025
A
Add float8 FakeQuantizeConfig and FakeQuantizer (#2735)
andrewor14 committed
August 5, 2025
A
Deprecate old QAT APIs (#2641)
andrewor14 committed
July 17, 2025
A
Clean up QAT API surface + add separate API ref (#2567)
andrewor14 committed
June 18, 2025
A
[BE] Convert quant_primitives methods private (#2350)
Apurva Jain committed
June 5, 2025
A
Add Float8ActInt4WeightQATQuantizer (#2289)
andrewor14 committed
June 3, 2025
A
Fix QAT range learning, ensure scales get gradients (#2280)
andrewor14 committed
May 29, 2025
A
Enable range learning for QAT
andrewor14 committed
April 21, 2025
A
Match QAT prepare and convert numerics exactly for bf16 and fp16 (#2060)
andrewor14 committed
January 17, 2025
A
Delete unused QAT utils code (#1579)
andrewor14 committed
November 12, 2024
A
Ruff Lint fixes (torchao/quantization) (#1244)
Apurva Jain committed
October 24, 2024
A
[reland] Move QAT out of prototype (#1152)
andrewor14 committed