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

Python bindings for llama.cpp

0 0 0 Python

COMMITS

09a4f78e05f43fcd93efc82cfddca250af1bad4d
July 9, 2024
A
fix(ci): Update LLAMA_ flags to GGML_
Andrei Betlen committed
09a4f78
A
fix: Update LLAMA_ flags to GGML_ flags
Andrei Betlen committed
1a55417
A
feat: Update llama.cpp
Andrei Betlen committed
218d361
July 6, 2024
A
fix: update token_to_piece
Andrei Betlen committed
157d913
A
feat: Update llama.cpp
Andrei Betlen committed
62804ee
July 4, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
7e20e34
July 2, 2024
A
chore: Bump version
Andrei Betlen committed
01bddd6
A
fix(ci): Update macos image (macos-11 is removed)
Andrei Betlen committed
3a551eb
A
feat: Update llama.cpp
Andrei Betlen committed
8992a1a
A
fix(misc): Fix type errors
Andrei Betlen committed
387d01d
A
fix(ci): Use LLAMA_CUDA for cuda wheels
Andrei Betlen committed
4fb6fc1
A
chore: Bump version
Andrei Betlen committed
b4cc923
A
feat: Update llama.cpp
Andrei Betlen committed
bd5d17b
A
fix(server): Fix bug in FastAPI streaming response where dependency was released before request completes causing SEGFAULT
Andrei Betlen committed
296304b
A
fix: Copy dependencies for windows
Andrei Betlen committed
dc20e8c
A
fix: Fix RPATH so it works on macos
Andrei Betlen committed
73fe013
A
fix: Fix installation location for shared libraries
Andrei Betlen committed
e51f200
A
fix: force $ORIGIN rpath for shared library files
Andrei Betlen committed
d5f6a15
A
fix: Update shared library rpath
Andrei Betlen committed
139774b
A
Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main
Andrei Betlen committed
92bad6e
A
misc: Install shared libraries to lib subdirectory
Andrei Betlen committed
c546c94
O
fix(ci): Fix the CUDA workflow (#1551)
oobabooga committed
73ddf29
A
fix(server): Update `embeddings=False` by default. Embeddings should be enabled by default for embedding models.
Andrei Betlen committed
bf5e0bb
A
feat: Update llama.cpp
Andrei Betlen committed
117cbb2
June 21, 2024
A
feat: Update llama_cpp.py bindings
Andrei Betlen committed
04959f1
D
chore(deps): bump pypa/cibuildwheel from 2.18.1 to 2.19.1 (#1527)
dependabot[bot] committed
35c980e
D
chore(deps): bump docker/build-push-action from 5 to 6 (#1539)
dependabot[bot] committed
398fe81
J
docs: Update readme examples to use newer Qwen2 model (#1544)
Jon Craton committed
27d5358
A
feat: Update llama.cpp
Andrei Betlen committed
5beec1a
June 20, 2024
A
docs: Remove references to deprecated opencl backend. Closes #1512
Andrei Betlen committed
d98a24a