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

Python bindings for llama.cpp

0 0 0 Python

COMMITS

v0.3.4-metal
December 9, 2024
A
chore: Bump version
Andrei Betlen committed
002f583
A
fix(ci): hotfix for wheels
Andrei Betlen committed
ca80802
A
chore: Bump version
Andrei Betlen committed
a9fe0f8
A
Add CUDA 12.5 and 12.6 to generated output wheels
Andrei Betlen committed
61508c2
A
feat: Update llama.cpp
Andrei Betlen committed
5585f8a
December 6, 2024
A
misc: Update run server command
Andrei Betlen committed
b9b50e5
A
Merge branch 'main' of github.com:abetlen/llama-cpp-python into main
Andrei Betlen committed
6889429
A
misc: Update development Makefile
Andrei Betlen committed
df136cb
A
fix: chat API logprobs format (#1788)
Adam Jones committed
4f0ec65
L
fix(examples): Refactor Batching notebook to use new sampler chain API (#1793)
Luke Stanley committed
d610477
F
fix(docs): Update development instructions (#1833)
Florents Tselai committed
1ea6154
G
fix: Avoid thread starvation on many concurrent requests by making use of asyncio to lock llama_proxy context (#1798)
Graeme Power committed
9bd0c95
I
fix: added missing exit_stack.close() to /v1/chat/completions (#1796)
Ignaz "Ian" Kraft committed
073b7e4
O
fix: Re-add suport for CUDA 12.5, add CUDA 12.6 (#1775)
Olivier DEBAUCHE committed
77a12a3
P
fix: make content not required in ChatCompletionRequestAssistantMessage (#1807)
Philippe Martin committed
4192210
R
docs: Remove ref to llama_eval in llama_cpp.py docs (#1819)
Rich Dougherty committed
38fbd29
D
fix logit-bias type hint (#1802)
ddh0 committed
fa04cdc
D
chore(deps): bump conda-incubator/setup-miniconda from 3.0.4 to 3.1.0 (#1821)
dependabot[bot] committed
ddac04c
A
Merge branch 'main' of github.com:abetlen/llama-cpp-python into main
Andrei Betlen committed
d553a54
A
fix: Fix pickling of Llama class by setting seed from _seed member. Closes #1769
Andrei Betlen committed
2523472
D
chore(deps): bump pypa/cibuildwheel from 2.21.1 to 2.22.0 (#1844)
dependabot[bot] committed
2795303
A
fix(ci): Remove CUDA 12.5 from index
Andrei Betlen committed
991d9cd
P
fix(ci): Remove cuda version 12.5.0 incompatibility with VS (#1838)
PΛBLØ ᄃΞ committed
4f17ae5
A
fix(ci): Update CMakeLists.txt for macos
Andrei Betlen committed
d5d5099
A
fix(ci): Use default architecture chosen by action
Andrei Betlen committed
d8cc231
A
fix(ci): Use python3
Andrei Betlen committed
b34f200
A
fix(ci): gg
Andrei Betlen committed
1cd3f2c
A
fix(ci): Install with regular pip
Andrei Betlen committed
df05096
A
fix(ci): Update config
Andrei Betlen committed
a412ba5
A
fix(ci): Debug print python system architecture
Andrei Betlen committed
9a09fc7