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/asinh.c

@@ -64,3 +64,7 @@ double asinh(double x)
 	}
 	return s ? -x : x;
 }
+
+#if LDBL_MANT_DIG == 53 && LDBL_MAX_EXP == 1024
+__strong_reference(asinh, asinhl);
+#endif