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

libc/tinymath/acos.c

@@ -141,3 +141,7 @@ double acos(double x)
 	w = R(z)*s+c;
 	return 2*(df+w);
 }
+
+#if LDBL_MANT_DIG == 53 && LDBL_MAX_EXP == 1024
+__strong_reference(acos, acosl);
+#endif