DeepSpeed
2d341405 - rename test_int4_quantization.py to test_intX_quantization.py

Commit

2 years ago

rename test_int4_quantization.py to test_intX_quantization.py

References

#4450 - adding 8bit dequantization kernel for asym fine-grained block quantization in zero-inference

Author

styoun

styoun

Committer

styoun

styoun

Parents

Loading