Jerry Zhang 1b51d29b66 [quant][pt2e] Enable constant folding for quantize ops (#109343) ... Summary: This PR added constant folding for quantize ops so that instead of storing fp32 weight in the quantized model, we'll get int8/int16 etc. weight Test Plan: python test/test_quantization.py TestQuantizePT2E.test_fold_quantize also will verify in executorch later Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D49399210](https://our.internmc.facebook.com/intern/diff/D49399210) Pull Request resolved: https://github.com/pytorch/pytorch/pull/109343 Approved by: https://github.com/kimishpatel, https://github.com/jgong5		2023-09-27 06:04:45 +00:00
..
test_duplicate_dq.py	[quant][pt2e] Enable constant folding for quantize ops (#109343)	2023-09-27 06:04:45 +00:00
test_graph_utils.py	[quant][pt2e] Rename _pt2e to pt2e (#104668)	2023-07-15 06:34:17 +00:00
test_metadata_porting.py	[quant][pt2e] Enable constant folding for quantize ops (#109343)	2023-09-27 06:04:45 +00:00
test_quantize_pt2e_qat.py	[quant][be] Move QAT tests to its own file (#108061)	2023-09-15 18:34:44 +00:00
test_quantize_pt2e.py	[quant][pt2e] Enable constant folding for quantize ops (#109343)	2023-09-27 06:04:45 +00:00
test_representation.py	[quant][pt2e] Enable constant folding for quantize ops (#109343)	2023-09-27 06:04:45 +00:00
test_x86inductor_quantizer.py	[quant][pt2e] Enable constant folding for quantize ops (#109343)	2023-09-27 06:04:45 +00:00