DeepSpeed
50cbfced - manual convert gpt-j fp32->fp16, seeing issues with fp16 revision

Commit

3 years ago

manual convert gpt-j fp32->fp16, seeing issues with fp16 revision

References

#1992 - [inference] test suite for ds-kernels (bert, roberta, gpt2, gpt-neo, gpt-j)

Author

jeffra

jeffra

Parents

Loading