DeepSpeed
aef8a856 - Extend quantization utils features (#2683)

Commit

2 years ago

Extend quantization utils features (#2683) * Extend quantization utils features * remove unwanted files * fix cahce setting Co-authored-by: Connor Holmes <connorholmes@microsoft.com>

References

#2683 - Extend quantization utils features

Author

lokoppakmsft

Parents

e7c14026

Files8

csrc
- includes
  - dequantization_utils.h
  - memory_access_utils.h
  - quantization.h
  - quantization_utils.h
- quantization
  - dequantize.cu
  - pt_binding.cpp
  - quantize.cu
tests/unit/ops/quantizer
- test_quantize.py

DeepSpeed aef8a856 - Extend quantization utils features (#2683)

DeepSpeed
aef8a856 - Extend quantization utils features (#2683)