Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
master-67c7779
67c77799
·
examples : add llama_init_from_gpt_params() common function (#1290)
·
May 02, 2023
master-0e6cbff
0e6cbff1
·
llama : fix compile warnings
·
May 02, 2023
master-5d5817c
5d5817ca
·
ggml : fix 32-bit ARM
·
May 02, 2023
master-8c9be35
8c9be35f
·
examples : improve vertical alignment of a few variables (#1286)
·
May 02, 2023
master-cc0bb72
cc0bb723
·
ggml : fix ppc64le build error and make cmake detect Power processors (#1284)
·
May 02, 2023
master-2bb992f
2bb992f0
·
llama : allow 0 as a seed number. (#1275)
·
May 02, 2023
master-e2cd506
e2cd5069
·
main : switch input_noecho to input_echo to remove negation (#979)
·
May 02, 2023
master-2d099e5
2d099e51
·
ggml: add names to tensors (#1268)
·
May 02, 2023
master-f4cef87
f4cef87e
·
Add git-based build information for better issue tracking (#1232)
·
May 01, 2023
master-58b367c
58b367c2
·
cuBLAS: refactor and optimize f16 mat mul performance (#1259)
·
May 01, 2023
master-ea3a0ad
ea3a0ad6
·
llama : update stubs for systems without mmap and mlock (#1266)
·
May 01, 2023
master-2bdc096
2bdc0964
·
ggml : fix ggml_used_mem() (#1264)
·
May 01, 2023
master-70269ca
70269cae
·
llama : fix session load / save (#1263)
·
May 01, 2023
master-b925f1f
b925f1f1
·
cuBLAS: fall back to pageable memory if pinned alloc fails (#1233)
·
May 01, 2023
master-90b19bd
90b19bd6
·
llama : let context be const when accessing const data (#1261)
·
May 01, 2023
master-7ff0dcd
7ff0dcd3
·
ggml : fix UB (int << 31)
·
Apr 30, 2023
master-6f79699
6f796992
·
build: add armv{6,7,8} support to cmake (#1251)
·
Apr 30, 2023
master-a5d30b1
a5d30b1f
·
common : better default number of threads (#934)
·
Apr 30, 2023
master-76a8849
76a88492
·
ggml : add CLBlast q5_0, q5_1, q8_0 dequant kernels (#1225)
·
Apr 30, 2023
master-6bc4400
6bc4400e
·
ggml : add Q5 WASM SIMD + GGML_FTYPE
·
Apr 30, 2023
Prev
1
…
81
82
83
84
85
86
87
88
89
…
98
Next