Xia, Weiwen 2cd3ef4777 Check scale dtype for fake_quantize_per_channel_affine_cachemask (#120987) ...

Fixes #120903

Scale for fake quant is assumed FP32 but not checked. If scales of double dtype are passed in, an internal error is raised: `TORCH_INTERNAL_ASSERT(!needs_dynamic_casting<func_t>::check(iter));` in aten/src/ATen/native/cpu/Loops.h
This PR adds a check of scale dtype.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/120987
Approved by: https://github.com/jgong5, https://github.com/jerryzh168

2024-03-30 07:32:32 +00:00

..

ao_migration

ao migration: remove package test as this behavior is tested by other things (#94422)

2023-02-13 16:33:40 +00:00

bc

[BE] Enable ruff's UP rules and autoformat test/ (#105434)

2023-07-19 20:36:06 +00:00

core

Check scale dtype for fake_quantize_per_channel_affine_cachemask (#120987)

2024-03-30 07:32:32 +00:00

eager

[BE]: Update flake8 to v6.1.0 and fix lints (#116591)

2024-01-03 06:04:44 +00:00

fx

[BE]: Apply RUF025 dict.fromkeys preview rule (#118637)

2024-01-30 20:46:54 +00:00

jit

[quant] Remove deprecated torch.jit.quantized APIs (#118406)

2024-01-27 18:32:45 +00:00

pt2e

[quant][pt2e] Enable observer sharing between different quantization specs (#122734)

2024-03-27 16:45:19 +00:00

serialized

[ao] fix incorrect integer cast on histogram observer bounds (#90355)

2022-12-12 20:30:44 +00:00

__init__.py

remediation of S205607

2020-07-17 17:19:47 -07:00