pytorch

mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00

Files

Wu, Chunyuan d7411c0cc1 [AOTI] add C shim for QConvPointWise (#138540 )

This PR adds C shim for `QConvPointWisePT2E` and `QConvPointWiseBinaryPT2E` similar to https://github.com/pytorch/pytorch/pull/138439. Besides that, we aligned the implementation of `qconv_pointwise` with `qlinear_pointwise` in the following aspects:
1. The parameter order of `qconv_pointwise` and `qlinear_pointwise` are quite different, we aligned the schema of `qconv_pointwise` to have similar parameter order as `qlinear_pointwise` to make it more consistent.
2. We always converted `x_scale` and `x_zero_point` to Tensors, just like in the lowering of `qlinear_pointwise`. This avoids the need to create two separate C APIs (one for `double x_scale` and `int64_t x_zero_point`, and another for `Tensor` versions). Instead, we only need one API for `Tensor`-based `x_scale` and `x_zero_point`. If we later add dynamic quantization for qconv (which will use `Tensor` for `x_scale` and `x_zero_point`), we can reuse the code from this PR and don't need to change the C shim layer API.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/138540
Approved by: https://github.com/jgong5, https://github.com/desertfire
ghstack dependencies: #138691, #138806

2024-10-31 02:03:01 +00:00

ao_migration

Enable UFMT on all of test/quantization/ao_migration &bc (#123994 )

2024-04-13 06:36:10 +00:00

Fix failures when default is flipped for weights_only (#127627 )

2024-08-16 00:22:43 +00:00

core

[AOTI] add C shim for QConvPointWise (#138540 )

2024-10-31 02:03:01 +00:00

eager

Add None return type to init -- tests (#132352 )

2024-08-01 15:44:51 +00:00