Xia, Weiwen 3b0cd9b542 [Quant][PT2E] add a lowering pass for x86 backend (#149708) ... **Summary** This PR adds a lowering pass for x86 backend - Patterns of `dequantize -> conv/linear (-> quantize)` are fused to corresponding quantized onednn ops. - Weights are prepacked ahead of time. - Post ops of conv/linear are fused if supported. - The pass returns a `GraphModule` with the modifications mentioned above. **Test plan** ``` pytest test/quantization/pt2e/test_x86inductor_quantizer.py -k test_lowering_to_x86 ``` Pull Request resolved: https://github.com/pytorch/pytorch/pull/149708 Approved by: https://github.com/jerryzh168, https://github.com/leslie-fang-intel		2025-04-01 17:32:41 +00:00
..
nn	Fix typo (#147330)	2025-02-18 20:20:34 +00:00
ns	[BE]: Apply ruff PERF403 to use dict comprehensions more often (#149257)	2025-03-18 00:46:07 +00:00
pruning	[BE] Upgrade to mypy 1.14 (#145966)	2025-03-04 20:58:26 +00:00
quantization	[Quant][PT2E] add a lowering pass for x86 backend (#149708)	2025-04-01 17:32:41 +00:00
__init__.py	[BE][Easy] improve submodule discovery for torch.ao type annotations (#144680)	2025-01-13 17:16:19 +00:00