3 Commits

Author	SHA1	Message	Date
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
Jerry Zhang	41e2189843	[quant] Remove reference representation rewrite for adaptive_avg_pool2d (#108924) ... Summary: integer adaptive_avg_pool2d is not well defined due to different possible ways of rounding fp32 value to integer value, and this op isn't too critical for numerics (since it appears not too often), so we'll skip this for now. we might need to revert the changes that adds integer impl for adaptive_avg_pool op as well Test Plan: python test/test_quantization.py TestQuantizePT2ERepresentation Reviewers: Subscribers: Tasks: Tags: Pull Request resolved: https://github.com/pytorch/pytorch/pull/108924 Approved by: https://github.com/kimishpatel	2023-09-14 10:18:36 +00:00
Jerry Zhang	c914ca7577	[quant][be] Add TestPT2ERepresentation test case (#108923) ... Summary: att Test Plan: python test/test_quantization.py TestPT2ERepresentation Reviewers: Subscribers: Tasks: Tags: Pull Request resolved: https://github.com/pytorch/pytorch/pull/108923 Approved by: https://github.com/andrewor14	2023-09-14 02:01:38 +00:00