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

Python bindings for llama.cpp

0 0 1 Python

COMMITS

/ llama_cpp/server/settings.py
main
September 20, 2024
A
feat: Add option to configure n_ubatch
Andrei Betlen committed
6c44a3f
July 9, 2024
A
fix(misc): Format
Andrei Betlen committed
c1ae815
July 2, 2024
A
fix(server): Update `embeddings=False` by default. Embeddings should be enabled by default for embedding models.
Andrei Betlen committed
bf5e0bb
June 4, 2024
N
feat: adding `rpc_servers` parameter to `Llama` class (#1477)
nullname committed
d634efc
May 5, 2024
A
feat(server): Add support for setting root_path. Closes #1420
Andrei Betlen committed
0318702
April 30, 2024
A
feat: Add option to enable `flash_attn` to Lllama params and ModelSettings
Andrei Betlen committed
22d77ee
April 26, 2024
A
fix: pydantic deprecation warning
Andrei Betlen committed
fcfea66
April 23, 2024
S
feat(server): Provide ability to dynamically allocate all threads if desired using `-1` (#1364)
Sean Bailey committed
53ebcc8
April 17, 2024
K
feat: add `disable_ping_events` flag (#1257)
khimaros committed
b73c73c
D
feat: Use all available CPUs for batch processing (#1345)
ddh0 committed
c96b2da
April 1, 2024
L
feat: add support for KV cache quantization options (#1307)
Limour committed
f165048
February 28, 2024
A
misc: Format
Andrei Betlen committed
727d60c
A
feat: Update llama.cpp
Andrei Betlen committed
0d37ce5
February 26, 2024
A
feat(server): Add support for pulling models from Huggingface Hub (#1222)
Andrei committed
4d574bd
A
fix: remove prematurely commited change
Andrei Betlen committed
dcf38f6
February 25, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
2292af5
February 17, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
fdce078
January 31, 2024
A
Add speculative decoding (#1120)
Andrei committed
fb762a6
January 29, 2024
A
Automatically set chat format from gguf (#1110)
Andrei committed
da003d8
January 19, 2024
A
feat: Add ability to load chat format from huggingface autotokenizer or tokenizer_config.json files.
Andrei Betlen committed
b8fc1c7
January 18, 2024
A
Offload KQV by default
Andrei Betlen committed
48c3b77
January 16, 2024
K
fix(cli): allow passing n_ctx=0 to openAI API server args to use model n_ctx_train field per #1015 (#1093)
Kyle Mistele committed
9c36688
January 15, 2024
A
Add split_mode option. Closes #1085
Andrei Betlen committed
84615ad
P
Implement GGUF metadata KV overrides (#1011)
Phil H committed
76aafa6
December 22, 2023
A
docs: add server config docs
Andrei Betlen committed
522aecb
D
[Feat] Multi model support (#931)
Dave committed
12b7f2f