0 0 213 C++

llamafile : improve sgemm.cpp (#6796)

* llamafile : improve sgemm.cpp

- Re-enable by default
- Fix issue described in #6716
- Make code more abstract, elegant, and maintainable
- Faster handling of weirdly shaped `m` an `n` edge cases

* Address review comments

* Help clang produce fma instructions

* Address review comments

Justine Tunney committed 2y ago

192090bae47960f0d38d4967abe398a5d190057e

Parent: e931888

Committed by GitHub <noreply@github.com> on 4/22/2024, 7:00:36 PM