mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-02-07 06:53:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
cosmopolitan/third_party
History
Justine Tunney 5a4cf9560f
Add support for new GGJT v2 quantizers 
This change makes quantized models (e.g. q4_0) go 10% faster on Macs
however doesn't offer much improvement for Intel PC hardware.

This change syncs llama.cpp 699b1ad7fe6f7b9e41d3cb41e61a8cc3ea5fc6b5
which recently made a breaking change to nearly all its file formats
without any migration. Since that'll break hundreds upon hundreds of
models on websites like HuggingFace llama.com will support both file
formats because llama.com will never ever break the GGJT file format
2023-05-13 08:08:32 -07:00
..
aarch64 Make Arm Neon intrinsics work with make tags 2023-05-12 18:32:53 -07:00
argon2 Fold LIBC_UNICODE into LIBC_STR 2022-08-13 08:42:32 -07:00
awk Make cli commands yoinkable into cosmo shell 2022-10-14 16:37:29 -07:00
bzip2 Make considerably more progress on AARCH64 2023-05-12 22:42:57 -07:00
chibicc Make considerably more progress on AARCH64 2023-05-12 22:42:57 -07:00
compiler_rt Make considerably more progress on AARCH64 2023-05-12 22:42:57 -07:00
ctags There must be only one clock() 2023-05-10 06:16:01 -07:00
dlmalloc Get LIBC_MEM and LIBC_STDIO building with aarch64 2023-05-10 04:20:47 -07:00
double-conversion Greatly expand system() shell code features 2022-10-11 21:30:31 -07:00
finger Fix Landlock Make so it can read pattern rule vars 2022-08-13 17:23:05 -07:00
gcc Make considerably more progress on AARCH64 2023-05-12 22:42:57 -07:00
gdtoa Fix build 2022-11-08 15:24:17 -08:00
getopt Mop up more test regressions 2023-05-13 01:09:44 -07:00
ggml Add support for new GGJT v2 quantizers 2023-05-13 08:08:32 -07:00
hiredis Fix MODE=asan build regression 2023-01-08 05:47:18 -08:00
intel Make further progress on non-x86 support 2023-05-10 04:20:47 -07:00
libcxx Fix some more issues with aarch64 and llama.cpp 2023-05-10 07:34:26 -07:00
linenoise bestline keybindings and redbean definitions (#678) 2022-11-06 00:28:08 -07:00
lua Fix bug in ASAN reporting 2023-02-02 02:28:58 -08:00
lz4cli Make progress towards aarch64 build 2023-05-10 04:20:46 -07:00
make Increase stack size to 128k and guard size to 16k 2022-12-18 22:58:29 -08:00
maxmind Fix bugs and make code tinier 2022-10-09 23:21:34 -07:00
mbedtls Get MbedTLS and its unit tests passing AARCH64 2023-05-11 21:53:15 -07:00
musl Remove a misplaced include 2023-02-23 08:10:38 -08:00
nsync Remove sys_getrandom() on NetBSD 2023-05-10 04:20:47 -07:00
puff Improve cosmocc toolchain 2023-03-05 23:52:49 -08:00
python Get MbedTLS and its unit tests passing AARCH64 2023-05-11 21:53:15 -07:00
qemu Get aarch64 hello world working 2023-05-10 04:20:47 -07:00
quickjs Add Intel intrinsics headers 2023-04-27 05:44:38 -07:00
radpajama Import radpajama (a redpajama.cpp fork) (#814) 2023-05-11 07:12:08 -07:00
regex Rename hidden keyword to _Hide 2022-11-08 12:55:28 -08:00
sed Make considerably more progress on AARCH64 2023-05-12 22:42:57 -07:00
smallz4 Pay off more technical debt 2022-09-12 23:36:56 -07:00
sqlite3 Make considerably more progress on AARCH64 2023-05-12 22:42:57 -07:00
stb Make considerably more progress on AARCH64 2023-05-12 22:42:57 -07:00
tidy Get repository to build with GCC 11 2022-09-13 04:14:55 -07:00
tr Fix MODE=opt build 2022-10-14 16:49:16 -07:00
unzip There must only be one strerror() 2023-05-10 15:34:13 -07:00
vqsort Make progress towards aarch64 build 2023-05-10 04:20:46 -07:00
xed Get aarch64 hello world working 2023-05-10 04:20:47 -07:00
zip Increase stack size to 128k and guard size to 16k 2022-12-18 22:58:29 -08:00
zlib Get LIBC_TESTLIB building on AARCH64 2023-05-11 19:57:09 -07:00
math.h Further optimize the math library 2023-04-28 01:20:47 -07:00
third_party.mk Import radpajama (a redpajama.cpp fork) (#814) 2023-05-11 07:12:08 -07:00