Make more ML improvements

- Fix UX issues with llama.com
- Do housekeeping on libm code
- Add more vectorization to GGML
- Get GGJT quantizer programs working well
- Have the quantizer keep the output layer as f16c
- Prefetching improves performance 15% if you use fewer threads
This commit is contained in:
Justine Tunney 2023-05-16 08:07:23 -07:00
parent 80db9de173
commit e7eb0b3070
No known key found for this signature in database
GPG key ID: BE714B4575D6E328
46 changed files with 340 additions and 289 deletions

View file

@ -24,7 +24,6 @@
#include "libc/runtime/runtime.h"
#include "libc/testlib/ezbench.h"
#include "libc/testlib/testlib.h"
#include "libc/tinymath/tinymath.h"
#include "libc/x/x.h"
float remainderf2(float, float);