Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

merge from upstream #21

Merged
merged 47 commits into from
May 27, 2024
Merged
Changes from 1 commit
Commits
Show all changes
47 commits
Select commit Hold shift + click to select a range
3e5faa8
cuda : fix rope + add tests (#7452)
ggerganov May 22, 2024
95fb0ae
CUDA: remove incorrect precision check (#7454)
JohannesGaessler May 22, 2024
9b3d833
cuda : fix compile warning (#7454)
ggerganov May 22, 2024
03d8900
llama : add missing model type names (#7445)
jart May 22, 2024
fcda112
vulkan: add workaround for iterator boundary check to fix clang-cl de…
Adriankhl May 22, 2024
b18532a
phi3 : duplicate rope factors in each layer (#7447)
slaren May 22, 2024
38c0347
CUDA: fix FA out-of-bounds writes (#7465)
JohannesGaessler May 22, 2024
6ff1398
common : normalize naming style (#7462)
ggerganov May 22, 2024
197ff91
build : remove zig (#7471)
ggerganov May 22, 2024
1e37436
SimpleChat: a simple and dumb web front end for testing /chat/complet…
hanishkvc May 22, 2024
cd93a28
CUDA: fix FA out-of-bounds reads (#7479)
JohannesGaessler May 22, 2024
fbf777d
main : minor (#7462)
ggerganov May 23, 2024
1b1e27c
Update vulkan rope implementation to support frequency factors (#7475)
0cc4m May 23, 2024
e84b71c
ggml : drop support for QK_K=64 (#7473)
ggerganov May 23, 2024
d48c88c
ggml : remove ggml_flash_attn and ggml_flash_ff (#7463)
ggerganov May 23, 2024
152da28
labeler.yml: add embedding label detector [no ci] (#7482)
mofosyne May 23, 2024
a61a94e
llama : rename n_ctx -> cache.size, less confusing (#0)
ggerganov May 23, 2024
9b82476
Add missing inference support for GPTNeoXForCausalLM (Pythia and GPT-…
fairydreaming May 23, 2024
dacfceb
readme : add GPT-NeoX + Pythia to the list of supported models (#7491)
felladrin May 23, 2024
55ac3b7
ci : use Pythia models instead of OpenLlama (#7470)
ggerganov May 23, 2024
3015851
llama : add getters for n_threads/n_threads_batch (#7464)
danbev May 23, 2024
8b94e79
readme : add Bunny in supported models [no ci] (#7469)
criminact May 23, 2024
007489e
Fix phi3 chat template confusion with zephyr (#7449)
tristandruyen May 23, 2024
1debe72
ggml : silence UB sanitizer error during iq2_xxs quantization (#0)
ggerganov May 23, 2024
74f33ad
readme : remove trailing space (#7469)
ggerganov May 23, 2024
0df0aa8
add build shared lib in win release package (#7438)
arthw May 24, 2024
fbca2f2
Add support for ArcticForCausalLM (#7020)
fairydreaming May 24, 2024
27891f6
docker.yml: disable light-intel and server-intel test (#7515)
mofosyne May 24, 2024
d041d2c
flake.lock: Update (#7232)
ggerganov May 24, 2024
b83bab1
gguf-py : fix and simplify quantized shape round-trip (#7483)
compilade May 25, 2024
5768433
Make tokenize CLI tool have nicer command line arguments. (#6188)
Noeda May 25, 2024
902184d
fix missing slash in `fs_get_cache_directory()` (#7503)
ngxson May 25, 2024
9791f40
android : module (#7502)
eltonkola May 25, 2024
faa0e69
ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)
msy-kato May 25, 2024
00c6390
main : don't print special tokens with --grammar (#6923)
jart May 25, 2024
3cbd23e
labeler: added Apple Metal detector (+Kompute) (#7529)
mofosyne May 25, 2024
9588f19
train : change default FA argument (#7528)
ggerganov May 25, 2024
b9adcbb
SimpleChat Completion Mode flexibility and cleanup, Settings gMe, Opt…
hanishkvc May 26, 2024
9146d36
Readme: add akx/ggify to tools (#1484)
akx May 26, 2024
c429b33
llama : add Smaug 70B support (#7402)
bartowski1182 May 26, 2024
32a2821
Fix aya-23 conversion scripts (#7539)
Galunid May 26, 2024
d298382
main: replace --no-special with --special (#7534)
mofosyne May 26, 2024
dff451c
flake.lock: Update (#7540)
ggerganov May 26, 2024
d6ef0e7
github: add self sorted issue ticket forms (#7543)
mofosyne May 27, 2024
eaf6e03
llama : add comments about experimental flags (#7544)
ggerganov May 27, 2024
62bfef5
metal : disable FA kernel for HS=256 (#7556)
ggerganov May 27, 2024
e111516
Merge branch 'layla-build' into merge
l3utterfly May 27, 2024
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
fix missing slash in fs_get_cache_directory() (ggml-org#7503)
* fix missing slash in fs_get_cache_directory()

* use LOCALAPPDATA for fs_get_cache_directory()

* better code style
  • Loading branch information
ngxson authored May 25, 2024

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
commit 902184dd3a9d6685e752b19027a48423742531db
16 changes: 10 additions & 6 deletions common/common.cpp
Original file line number Diff line number Diff line change
@@ -1855,11 +1855,15 @@ bool fs_create_directory_with_parents(const std::string & path) {

std::string fs_get_cache_directory() {
std::string cache_directory = "";
auto ensure_trailing_slash = [](std::string p) {
// Make sure to add trailing slash
if (p.back() != DIRECTORY_SEPARATOR) {
p += DIRECTORY_SEPARATOR;
}
return p;
};
if (getenv("LLAMA_CACHE")) {
cache_directory = std::getenv("LLAMA_CACHE");
if (cache_directory.back() != DIRECTORY_SEPARATOR) {
cache_directory += DIRECTORY_SEPARATOR;
}
} else {
#ifdef __linux__
if (std::getenv("XDG_CACHE_HOME")) {
@@ -1870,12 +1874,12 @@ std::string fs_get_cache_directory() {
#elif defined(__APPLE__)
cache_directory = std::getenv("HOME") + std::string("/Library/Caches/");
#elif defined(_WIN32)
cache_directory = std::getenv("APPDATA");
cache_directory = std::getenv("LOCALAPPDATA");
#endif // __linux__
cache_directory = ensure_trailing_slash(cache_directory);
cache_directory += "llama.cpp";
cache_directory += DIRECTORY_SEPARATOR;
}
return cache_directory;
return ensure_trailing_slash(cache_directory);
}