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

Python bindings for llama.cpp

0 0 4 Python

COMMITS

/ llama_cpp/server/__main__.py
batch-processing
December 22, 2023
D
[Feat] Multi model support (#931)
Dave committed
12b7f2f
December 12, 2023
R
Add support for running the server with SSL (#994)
Radoslav Gerganov committed
8e44a32
September 15, 2023
A
Remove confusing helpstring from server cli args. Closes #719
Andrei Betlen committed
b047b30
September 14, 2023
A
Fix boolean env vars and cli arguments
Andrei Betlen committed
0449d29
A
Fix boolean cli flags
Andrei Betlen committed
c999325
A
Fix tensor_split cli option
Andrei Betlen committed
c4c440b
September 13, 2023
A
Fix issue with Literal and Optional cli arguments not working. Closes #702
Andrei Betlen committed
759405c
July 9, 2023
A
bugfix: pydantic settings missing / changed fields
Andrei Betlen committed
6f70cc4
July 8, 2023
A
Upgrade fastapi to 0.100.0 and pydantic v2
Andrei Betlen committed
52753b7
June 11, 2023
G
correction to add back environment variable support <3 docker
Gabor committed
3129a0e
June 10, 2023
G
fixes abetlen/llama-cpp-python #358
Gabor committed
3ea3193
May 8, 2023
A
Bugfix: not falling back to environment variables when default is value is set.
Andrei Betlen committed
29f094b
A
Show default value when --help is called
Andrei Betlen committed
0d6c600
A
Use environment variable if parsed cli arg is None
Andrei Betlen committed
022e9eb
May 5, 2023
A
Add cli options to server. Closes #37
Andrei Betlen committed
24fc387
May 2, 2023
A
Refactor server to use factory
Andrei Betlen committed
9eafc4c
April 29, 2023
L
llama_cpp server: slight refactor to init_llama function
Lucas Doyle committed
efe8e6f
L
llama_cpp server: app is now importable, still runnable as a module
Lucas Doyle committed
468377b
April 25, 2023
A
Update n_batch for server
Andrei Betlen committed
3cab3ef
April 19, 2023
A
Add use_mmap flag to server
Andrei Betlen committed
e4647c7
April 15, 2023
A
Add experimental cache
Andrei Betlen committed
92c0771
April 14, 2023
A
Fix completion request
Andrei Betlen committed
6c7cec0
April 13, 2023
A
Formatting
Andrei Betlen committed
4f5f99e
April 12, 2023
A
Enable logprobs on completion endpoint
Andrei Betlen committed
0daf16d
A
Fix threading bug. Closes #62
Andrei Betlen committed
19598ac
A
Implement logprobs parameter for text completion. Closes #2
Andrei Betlen committed
b3805bb
April 11, 2023
A
Remove async from function signature to avoid blocking the server
Andrei Betlen committed
213cc5c
April 8, 2023
A
Formatting
Andrei Betlen committed
0067c1a
April 7, 2023
A
Safer calculation of default n_threads
Andrei Betlen committed
da539cc
A
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
Andrei Betlen committed
930db37
A
Handle prompt list
Andrei Betlen committed
55279b6
April 5, 2023
M
Set n_batch to default values and reduce thread count:
MillionthOdin16 committed
c283edd
M
Set n_batch to the default value of 8. I think this is leftover from when n_ctx was missing and n_batch was 2048.
MillionthOdin16 committed
76a82ba
A
Add server as a subpackage
Andrei Betlen committed
44448fb