llama.cpp
ea5d7478 - sgemm : improved Q4_0 and Q8_0 performance via 4xN and Mx4 gemm (#8908)

Commit

1 year ago

sgemm : improved Q4_0 and Q8_0 performance via 4xN and Mx4 gemm (#8908)

References

#8908 - Introduction of gemm4xN and gemmMx4 for Q4_0 and Q8_0 for better performance results

Author

Srihari-mcw

Srihari-mcw

Parents

Loading