Rafik Saliev
Rafik Saliev
Thank you @slaren for your response. > Looks interesting, though if it is not possible to implement support for quantized types using oneDNN, its usefulness may be limited. oneDNN supports...
@slaren, can you please help me understand how a backend should work in `gpt-2-sched` sample? I tried to enable BLAS backend in the sample, but do not see any call...
Thank you, `main: number of tokens in prompt = 40,` - solved the issue.
Hello, I"ve published the new simplified backend version based on the logic of BLAS backend. Added also simple MUL_MAT+ADD fusing and weights 'pre-packing' (reordering) features. The 'pre-packing' executed at schedule...
Closing due to #6329