Zhicheng Yan 77643ed2eb [torch quantization]raise exception when OOM during combine histogram in observer (#123309) ... Summary: Even with changes in D55347133, it is still possible to OOM in histogram observer, because the size of allocated tensor also depends on *downsample_rate*. For example, I still see OOM due to the attempt of allocating a 10GB+ histogram tensor in multi-task model. To fix OOM issue better, we use *try-catch* clause to avoid OOM. Empirically, we set the max size of a single histogram tensor size to 1 GB. Test Plan: Test the change for Multi-Task model (depth + segmentation) Differential Revision: D55567292 Pull Request resolved: https://github.com/pytorch/pytorch/pull/123309 Approved by: https://github.com/jerryzh168		2024-04-06 03:15:02 +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	[torch quantization]raise exception when OOM during combine histogram in observer (#123309)	2024-04-06 03:15:02 +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	[dynamo, 3.12] enable tests disabled due to missing dynamo 3.12 support (#123300)	2024-04-05 20:13:17 +00:00
serialized
__init__.py