Skip to content
GitLab
Explore
Sign in
Overview
Active
Stale
All
This project is mirrored from
https://github.com/ggerganov/llama.cpp
. Pull mirroring updated
Sep 20, 2024
.
ceb/perf-faster-multigpu
6272b676
·
use stride=128 if built for tensor cores
·
Nov 27, 2023
fix-op-array-bounds
d85b9bfe
·
ggml : fix -Warray-bounds warning with gcc
·
Nov 26, 2023
lookahead
8d8b76d4
·
lookahead : add comments
·
Nov 26, 2023
server-oai-compat
21b70bab
·
straightforward /v1/models endpoint
·
Nov 24, 2023
kv-cache-opts
f8e9f114
·
common : add -dkvc arg for enabling kv cache dumps
·
Nov 23, 2023
cuda-stablelm-rope
84adb541
·
add n_dims parameter to llm_build_k_shift, default to n_rot via overload
·
Nov 22, 2023
jinja-meta
b044ba7a
·
gguf-py : initialize chat_template
·
Nov 18, 2023
llama-max-nodes
573aefa7
·
llama : increase max nodes
·
Nov 17, 2023
gg/units
63d85d16
·
llama : disambiguate data units
·
Nov 16, 2023
ceb/fix-yarn-neox
f8249026
·
YaRN : correction to GPT-NeoX implementation
·
Nov 15, 2023
cuda-graph-size
b4a36f40
·
ggml-cuda : increase max graph size
·
Nov 15, 2023
ceb/restore-prefix-space
5e899428
·
do not add space prefix if the first token is special
·
Nov 14, 2023
fix-llava-regression-sq-img
59254360
·
llava : fix regression for square images in #3613
·
Nov 13, 2023
fix-gguf-convert-endian
b226d07d
·
Bump version and upd description
·
Nov 11, 2023
llama-metadata
d0445a2e
·
better documentation
·
Nov 10, 2023
backend-alloc-v-fix
3469f5a9
·
ggml-alloc : fix backend assignments of views
·
Nov 08, 2023
fix-libllava-ld
1b723a8d
·
make : do not add linker flags when compiling static llava lib
·
Nov 07, 2023
fix-tensor-split-zero
47d604fa
·
fix issues
·
Nov 05, 2023
revert-pool
3ef358ff
·
Revert "cuda : use CUDA memory pool with async memory allocation/deallocation...
·
Nov 04, 2023
yet-another-yarn-fix
88ff0e39
·
common : YAYF (yet another YARN fix)
·
Nov 03, 2023
Prev
1
…
10
11
12
13
14
15
16
17
18
…
26
Next