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

Python bindings for llama.cpp

0 0 1 Python

COMMITS

36668331074c79f40494b51e4d541cd03601b9f2
May 5, 2024
O
feat(ci): Add docker checks and check deps more frequently (#1426)
Olivier DEBAUCHE committed
3666833
A
feat: Update llama.cpp
Andrei Betlen committed
3e2597e
May 4, 2024
N
fix: detokenization case where first token does not start with a leading space (#1375)
Noam Gat committed
e0d7674
J
feat: Implement streaming for Functionary v2 + Bug fixes (#1419)
Jeffrey Fong committed
1f56c64
May 3, 2024
A
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
Andrei Betlen committed
f9b7221
A
fix: Use memmove to copy str_value kv_override. Closes #1417
Andrei Betlen committed
9f7a855
A
feat(server): Remove temperature bounds checks for server. Closes #1384
Andrei Betlen committed
0a454be
D
fix(server): Propagate `flash_attn` to model load. (#1424)
Daniel Thuerck committed
2138561
May 2, 2024
A
chore: Bump version
Andrei Betlen committed
2117122
A
feat: Update llama.cpp
Andrei Betlen committed
d75dea1
A
feat: Add llama-3-vision-alpha chat format
Andrei Betlen committed
31b1d95
April 30, 2024
A
fix: Change default verbose value of verbose in image chat format handlers to True to match Llama
Andrei Betlen committed
4f01c45
A
feat: Update llama.cpp
Andrei Betlen committed
946156f
A
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
Andrei Betlen committed
9286b5c
A
fix: Suppress all logs when verbose=False, use hardcoded fileno's to work in colab notebooks. Closes #796 Closes #729
Andrei Betlen committed
f116175
J
fix: UTF-8 handling with grammars (#1415)
Jonathan Soma committed
3226b3c
A
docs: Change all examples from interpreter style to script style.
Andrei Betlen committed
945c62c
A
docs: Update README.md
Andrei Betlen committed
26478ab
A
chore: Bump version
Andrei Betlen committed
b14dd98
A
fix: wrong parameter for flash attention in pickle __getstate__
Andrei Betlen committed
29b6e9a
A
feat: Add option to enable `flash_attn` to Lllama params and ModelSettings
Andrei Betlen committed
22d77ee
A
feat: Update llama.cpp
Andrei Betlen committed
8c2b24d
O
fix(ci): Fix build-and-release.yaml (#1413)
Olivier DEBAUCHE committed
6332527
A
docs: Update README to include CUDA 12.4 wheels
Andrei Betlen committed
c8cd8c1
A
chore: Bump version
Andrei Betlen committed
f417cce
A
fix: Ensure image renders before text in chat formats regardless of message content order.
Andrei Betlen committed
3489ef0
A
fix(ci): Fix bug in use of upload-artifact failing to merge multiple artifacts into a single release.
Andrei Betlen committed
d03f15b
A
chore: Bump version
Andrei Betlen committed
26c7876
A
feat: Generic Chat Formats, Tool Calling, and Huggingface Pull Support for Multimodal Models (Obsidian, LLaVA1.6, Moondream) (#1147)
Andrei committed
fe2da09
A
feat: Update llama.cpp
Andrei Betlen committed
97fb860