happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
7,556 Commits 516 Branches 5,136 Tags 1,006 MiB

Default Branch

master

4fd59e8427 · ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON (#18413) · Updated 2025-12-27 17:33:14 -08:00
 ZIP  TAR.GZ

Branches

gguf-pip

0248ca811e · gguf : add notes for tests · Updated 2023-08-24 23:08:05 -07:00    happyz

6500
10
 ZIP  TAR.GZ
fix-eos

977629a34e · Merge branch 'master' into fix-eos · Updated 2023-08-23 12:40:19 -07:00    happyz

6516
4
 ZIP  TAR.GZ
gguf

66a66a05a8 · readme : add notice about new file format · Updated 2023-08-21 12:42:14 -07:00    happyz

6545
253
 ZIP  TAR.GZ
gguf-write-single-pass

6a9e6375b5 · gguf.py : indentation · Updated 2023-08-17 11:53:15 -07:00    happyz

6560
205
 ZIP  TAR.GZ
server-cfg

28046d1e52 · Merge and update · Updated 2023-08-08 14:36:11 -07:00    happyz

6613
12
 ZIP  TAR.GZ
gguf-write-tensor

511055722e · undo formatting · Updated 2023-07-27 23:09:14 -07:00    happyz

6642
26
 ZIP  TAR.GZ
gguf-python

af1c9966c8 · gguf : start write tensor info · Updated 2023-07-27 00:32:31 -07:00    happyz

6642
15
 ZIP  TAR.GZ
ggml-backends

d273bfd2c9 · allocator: cleanup, more comments · Updated 2023-07-22 06:05:24 -07:00    happyz

6713
21
 ZIP  TAR.GZ
ggml-backends-metal

d45c1631bc · metal : rewrite to fit new backend interface correctly (WIP) · Updated 2023-07-20 12:51:19 -07:00    happyz

6713
18
 ZIP  TAR.GZ
refactor-mpi

0492363137 · mpi : fix after master merge · Updated 2023-07-09 12:23:04 -07:00    happyz

6744
21
 ZIP  TAR.GZ
llama_server_completions

26cc1bd7a2 · llama : uniform variable names + struct init · Updated 2023-07-05 13:22:17 -07:00    happyz

6761
4
 ZIP  TAR.GZ
llama_server_timings

ff6e39f138 · use javascript generators as much cleaner API · Updated 2023-07-05 12:03:01 -07:00    happyz

6774
20
 ZIP  TAR.GZ
test-mac-os-ci

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

6771
5
 ZIP  TAR.GZ
try-fix-metal

5cc672a9a5 · metal : try to utilize more of the shared memory using smaller views · Updated 2023-06-26 12:23:04 -07:00    happyz

6808
1
 ZIP  TAR.GZ
avoid-gnu-source

78fafcaf10 · ggml : do not use _GNU_SOURCE gratuitously · Updated 2023-06-25 07:21:02 -07:00    happyz

6816
1
 ZIP  TAR.GZ
fix_clblast

20054a38c1 · Fix directory name · Updated 2023-05-26 16:00:08 -07:00    happyz

6966
1
 ZIP  TAR.GZ
chunks

a1cdd29cd2 · ggml : rms_norm in chunks · Updated 2023-05-20 00:15:54 -07:00    happyz

6987
2
 ZIP  TAR.GZ
steering

95dc4d7270 · Merge 'origin/master' into steering · Updated 2023-05-19 13:19:57 -07:00    happyz

6989
9
 ZIP  TAR.GZ
f16c

40ec4882c4 · ggml : use F16C conversion when available · Updated 2023-05-17 10:05:51 -07:00    happyz

6998
1
 ZIP  TAR.GZ
dequantize-matmul-3-gg

a3e6d62283 · cuda : alternative q4_q8 kernel · Updated 2023-05-12 07:02:39 -07:00    happyz

7032
8
 ZIP  TAR.GZ