Justine Tunney e7eb0b3070 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		2023-05-16 08:07:23 -07:00
..
calls	Perform some code cleanup	2023-05-15 16:32:10 -07:00
dns	Rename rand64() to _rand64()	2022-10-10 04:12:06 -07:00
fmt	Port a lot more code to AARCH64	2023-05-14 09:37:26 -07:00
intrin	Perform some code cleanup	2023-05-15 16:32:10 -07:00
log	Port a lot more code to AARCH64	2023-05-14 09:37:26 -07:00
mem	Make considerably more progress on AARCH64	2023-05-12 22:42:57 -07:00
nexgen32e	Make AARCH64 harder, better, faster, stronger	2023-05-15 02:15:34 -07:00
release	Port a lot more code to AARCH64	2023-05-14 09:37:26 -07:00
runtime	Port a lot more code to AARCH64	2023-05-14 09:37:26 -07:00
sock	Port a lot more code to AARCH64	2023-05-14 09:37:26 -07:00
stdio	Port a lot more code to AARCH64	2023-05-14 09:37:26 -07:00
str	Make more ML improvements	2023-05-16 08:07:23 -07:00
thread	Port a lot more code to AARCH64	2023-05-14 09:37:26 -07:00
time	Make fixes and improvements	2022-10-19 07:19:19 -07:00
tinymath	Make more ML improvements	2023-05-16 08:07:23 -07:00
x	Greatly expand system() shell code features	2022-10-11 21:30:31 -07:00
xed	Pay off more technical debt	2022-09-12 23:36:56 -07:00
zipos	Add fexecve() and map O_EXEC to O_PATH on Linux	2022-10-02 09:15:46 -07:00
test.mk	Don't relocate file descriptor memory	2022-09-09 16:54:28 -07:00