pytorch

mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00

Files

Jerry Zhang 938803df94 Add bfloat16 support for per tensor/channel cpu/cuda fake quantize ops (#139306 )

Summary: Fixes https://fb.workplace.com/groups/2240361332735959/permalink/8190736677698365

Test Plan:
buck2 test 'fbcode//mode/dev' fbcode//caffe2/test/quantization:test_quantization -- --exact 'caffe2/test/quantization:test_quantization - test_forward_per_channel_cachemask_cpu (caffe2.test.quantization.core.test_workflow_ops.TestFakeQuantizeOps)'

buck2 test 'fbcode//mode/dev-nosan' fbcode//caffe2/test/quantization:test_quantization -- --exact 'caffe2/test/quantization:test_quantization - test_forward_per_tensor_cachemask_cpu (caffe2.test.quantization.core.test_workflow_ops.TestFakeQuantizeOps)'

buck2 test 'fbcode//mode/dev-nosan' fbcode//caffe2/test/quantization:test_quantization -- --exact 'caffe2/test/quantization:test_quantization - test_forward_per_channel_cachemask_cuda (caffe2.test.quantization.core.test_workflow_ops.TestFakeQuantizeOps)'

buck2 test 'fbcode//mode/dev-nosan' fbcode//caffe2/test/quantization:test_quantization -- --exact 'caffe2/test/quantization:test_quantization - test_forward_per_channel_cachemask_cpu (caffe2.test.quantization.core.test_workflow_ops.TestFakeQuantizeOps)'

Differential Revision: D65221710

Pull Request resolved: https://github.com/pytorch/pytorch/pull/139306
Approved by: https://github.com/navsud

2024-10-31 20:41:15 +00:00

ao_migration

Enable UFMT on all of test/quantization/ao_migration &bc (#123994 )

2024-04-13 06:36:10 +00:00

Fix failures when default is flipped for weights_only (#127627 )

2024-08-16 00:22:43 +00:00

core

Add bfloat16 support for per tensor/channel cpu/cuda fake quantize ops (#139306 )

2024-10-31 20:41:15 +00:00

eager

Add None return type to init -- tests (#132352 )

2024-08-01 15:44:51 +00:00