Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
This project is mirrored from
https://github.com/ggerganov/llama.cpp
. Pull mirroring updated
Sep 19, 2024
.
b3726
b34e0234
·
musa: remove Clang builtins mapping (#9421)
·
Sep 11, 2024
b3725
51b60386
·
sycl : update support conditions (#9394)
·
Sep 11, 2024
b3723
6cd4e034
·
arg : bring back missing ifdef (#9411)
·
Sep 10, 2024
b3722
8d300bd3
·
enable --special arg for llama-server (#9419)
·
Sep 10, 2024
b3721
49006c67
·
llama : move random seed generation to the samplers (#9398)
·
Sep 10, 2024
b3720
00ba2ff7
·
metal : fix compile warning with GGML_METAL_NDEBUG (#0)
·
Sep 10, 2024
b3718
0b4ac757
·
RWKV v6: Add time_mix_decay_w1/w2 in quant exclusion list (#9387)
·
Sep 10, 2024
b3717
fb3f2498
·
make : do not run llama-gen-docs when building (#9399)
·
Sep 10, 2024
b3716
bfe76d4a
·
common : move arg parser code to `arg.cpp` (#9388)
·
Sep 09, 2024
b3715
293bebe0
·
rpc : fix segfault with nkvo (#9389)
·
Sep 09, 2024
b3714
5fac4d57
·
ggml : vector length agnostic SVE support (#9290)
·
Sep 09, 2024
b3713
5fb5e248
·
llama : minor sampling refactor (2) (#9386)
·
Sep 09, 2024
b3711
8e6e2fbe
·
CUDA: fix variable name conflict for Windows build (#9382)
·
Sep 09, 2024
b3707
daa9623a
·
Overlap cmdbuffer creation and cmdbuffer execution in Vulkan backend by...
·
Sep 08, 2024
b3706
e079bffb
·
cuda : fix FA Q src index (1 -> 0) (#9374)
·
Sep 08, 2024
b3705
3f7ccfd6
·
common : bring back missing args, add env var duplication check (#9375)
·
Sep 08, 2024
b3704
a249843d
·
common : restore --n-gpu-layers (#9371)
·
Sep 08, 2024
b3703
19f4a7b2
·
llama : refactor samplers internal implementation (#9370)
·
Sep 08, 2024
b3702
2a358fb0
·
[SYCL] add check malloc result on device (#9346)
·
Sep 08, 2024
b3701
eae59718
·
llama : sanitize tokens in the upper bound (#9359)
·
Sep 08, 2024
Prev
1
2
3
4
5
6
7
…
122
Next