[quant] Add saturate_to_fp16 op for FP16 quant support (#42147)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/42147
Op to check the range of a tensor and clamp the values to fp16 range
This operator will be inserted into the graph in subsequent diffs.
Test Plan:
python test/test_quantization.py TestQuantizedTensor.test_fp16_saturate_op
Imported from OSS
Reviewed By: jerryzh168
Differential Revision: D22849221
fbshipit-source-id: 0da3298e179750f6311e3a09596a7b8070509096