MORPH
SIGN IN SIGN UP
abetlen / llama-cpp-python UNCLAIMED

Python bindings for llama.cpp

0 0 16 Python

COMMITS

v0.2.5
September 14, 2023
A
Bump version
Andrei Betlen committed
24fec0b
A
Fix issue installing on m1 macs
Andrei Betlen committed
dbd3a6d
A
Revert "Update llama.cpp"
Andrei Betlen committed
482ecd7
A
Update llama.cpp
Andrei Betlen committed
f73e385
A
Revert "Update llama.cpp"
Andrei Betlen committed
ca4eb95
A
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
Andrei Betlen committed
7da8e0f
A
Update base_path to fix issue resolving dll in windows isolation container.
Andrei Betlen committed
8474665
J
Update examples from ggml to gguf and add hw-accel note for Web Server (#688)
Jason Cox committed
40b2290
A
Update llama.cpp
Andrei Betlen committed
aa2f8a5
A
Fix dockerfiles to install starlette-context
Andrei Betlen committed
2291798
A
Enable make fallback for scikit-build-core
Andrei Betlen committed
65a2a20
A
Add documentation and changelog links in pyproject
Andrei Betlen committed
255d653
A
Upgrade pip for editable installs
Andrei Betlen committed
95d5480
A
Bump version
Andrei Betlen committed
507bcc7
A
Update CHANGELOG
Andrei Betlen committed
3e2250a
A
Update CHANGELOG
Andrei Betlen committed
60119db
A
Fix boolean env vars and cli arguments
Andrei Betlen committed
0449d29
E
Update app.py (#705)
earonesty committed
58a6e42
A
Add numa support, low level api users must now explicitly call llama_backend_init at the start of their programs.
Andrei Betlen committed
f4090a0
A
Fix boolean cli flags
Andrei Betlen committed
c999325
A
Update CHANGELOG
Andrei Betlen committed
83764c5
A
Format
Andrei Betlen committed
4daf77e
A
Update server params. Added lora_base, lora_path, low_vram, and main_gpu. Removed rms_norm_eps and n_gqa (deprecated in llama.cpp)
Andrei Betlen committed
2920c4b
A
Reorder init params to match llama.cpp order
Andrei Betlen committed
6a20293
A
Explicitly make all init params other than model_path into keyword only params
Andrei Betlen committed
c8f9b8a
A
Add kwargs to init to catch extra params
Andrei Betlen committed
a68f9e2
A
remove print
Andrei Betlen committed
9e345a4
A
Convert missed llama.cpp constants into standard python types
Andrei Betlen committed
517f9ed
A
Fix tensor_split cli option
Andrei Betlen committed
c4c440b
September 13, 2023
A
Bump version
Andrei Betlen committed
203ede4