ggml-org/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-29 22:53:58 +08:00
Code Issues Packages Projects Releases Wiki Activity
11,256 Commits 828 Branches 7,650 Tags

Default Branch

master

c85b92c69c · tests : adjust server string regex to also match m2 utlra results (#29648) · Updated 2026-09-29 20:32:35 +08:00
 ZIP  TAR.GZ

Branches

ggml-backends-metal

d45c1631bc · metal : rewrite to fit new backend interface correctly (WIP) · Updated 2023-07-21 03:51:19 +08:00    tqcq

10213
18
 ZIP  TAR.GZ
refactor-mpi

0492363137 · mpi : fix after master merge · Updated 2023-07-10 03:23:04 +08:00    tqcq

10244
21
 ZIP  TAR.GZ
llama_server_completions

26cc1bd7a2 · llama : uniform variable names + struct init · Updated 2023-07-06 04:22:17 +08:00    tqcq

10261
4
 ZIP  TAR.GZ
llama_server_timings

ff6e39f138 · use javascript generators as much cleaner API · Updated 2023-07-06 03:03:01 +08:00    tqcq

10274
20
 ZIP  TAR.GZ
test-mac-os-ci

f46db27ea0 · ci : disable FMA on Mac OS · Updated 2023-07-05 23:29:08 +08:00    tqcq

10271
5
 ZIP  TAR.GZ
try-fix-metal

5cc672a9a5 · metal : try to utilize more of the shared memory using smaller views · Updated 2023-06-27 03:23:04 +08:00    tqcq

10308
1
 ZIP  TAR.GZ
avoid-gnu-source

78fafcaf10 · ggml : do not use _GNU_SOURCE gratuitously · Updated 2023-06-25 22:21:02 +08:00    tqcq

10316
1
 ZIP  TAR.GZ
fix_clblast

20054a38c1 · Fix directory name · Updated 2023-05-27 07:00:08 +08:00    tqcq

10466
1
 ZIP  TAR.GZ
chunks

a1cdd29cd2 · ggml : rms_norm in chunks · Updated 2023-05-20 15:15:54 +08:00    tqcq

10487
2
 ZIP  TAR.GZ
steering

95dc4d7270 · Merge 'origin/master' into steering · Updated 2023-05-20 04:19:57 +08:00    tqcq

10489
9
 ZIP  TAR.GZ
f16c

40ec4882c4 · ggml : use F16C conversion when available · Updated 2023-05-18 01:05:51 +08:00    tqcq

10498
1
 ZIP  TAR.GZ
dequantize-matmul-3-gg

a3e6d62283 · cuda : alternative q4_q8 kernel · Updated 2023-05-12 22:02:39 +08:00    tqcq

10532
8
 ZIP  TAR.GZ
remove-vzip

e116eb638c · ggml : speed-up Q5_0 + Q5_1 at 4 threads · Updated 2023-05-11 23:51:56 +08:00    tqcq

10534
20
 ZIP  TAR.GZ
jed/spm-clblast

4baa85633a · Fix build · Updated 2023-05-07 09:44:07 +08:00    tqcq

10542
5
 ZIP  TAR.GZ
ci_cublas

31ff9e2e83 · ci : add cublas to windows release · Updated 2023-05-04 05:21:20 +08:00    tqcq

10557
1
 ZIP  TAR.GZ
q4_3-range-fix

102cd98074 · ggml : Q4_3c using 2x "Full range" approach · Updated 2023-04-23 19:56:44 +08:00    tqcq

10638
8
 ZIP  TAR.GZ
q4_0-q4_2-range-fix

71e6ae3779 · ggml : continue from #729 (wip) · Updated 2023-04-22 23:49:07 +08:00    tqcq

10682
7
 ZIP  TAR.GZ
gg/rmse_quantization

a0242a833c · Minor, plus rebase on master · Updated 2023-04-22 22:07:10 +08:00    tqcq

10682
2
 ZIP  TAR.GZ
quant-attn

4b8d5e3890 · llama : quantize attention results · Updated 2023-04-22 16:35:13 +08:00    tqcq

10687
1
 ZIP  TAR.GZ
mmap-pages-stats

1506737499 · Add mmap pages stats (disabled by default) · Updated 2023-04-17 00:22:30 +08:00    tqcq

10737
1
 ZIP  TAR.GZ