baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge pull request #29 from MillionthOdin16/main

Browse source 
Fixes and Tweaks to Defaults
This commit is contained in:
Andrei 2023-04-06 21:06:31 -04:00 committed by GitHub
commit c2e690b326
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 8 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.gitignore vendored
View file

@ -163,4 +163,4 @@ cython_debug/
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear # and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder. # option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/ .idea/

6
examples/high_level_api/fastapi_server.py
View file

@ -27,10 +27,10 @@ from sse_starlette.sse import EventSourceResponse
class Settings(BaseSettings): class Settings(BaseSettings):
model: str model: str
n_ctx: int = 2048 n_ctx: int = 2048
n_batch: int = 2048 n_batch: int = 8
n_threads: int = os.cpu_count() or 1 n_threads: int = int(os.cpu_count() / 2) or 1
f16_kv: bool = True f16_kv: bool = True
use_mlock: bool = True use_mlock: bool = False # This causes a silent failure on platforms that don't support mlock (e.g. Windows) took forever to figure out...
embedding: bool = True embedding: bool = True
last_n_tokens_size: int = 64 last_n_tokens_size: int = 64

6
llama_cpp/server/__main__.py
View file

@ -27,10 +27,10 @@ from sse_starlette.sse import EventSourceResponse
class Settings(BaseSettings): class Settings(BaseSettings):
model: str model: str
n_ctx: int = 2048 n_ctx: int = 2048
n_batch: int = 2048 n_batch: int = 8
n_threads: int = os.cpu_count() or 1 n_threads: int = int(os.cpu_count() / 2) or 1
f16_kv: bool = True f16_kv: bool = True
use_mlock: bool = True use_mlock: bool = False # This causes a silent failure on platforms that don't support mlock (e.g. Windows) took forever to figure out...
embedding: bool = True embedding: bool = True
last_n_tokens_size: int = 64 last_n_tokens_size: int = 64

1
setup.py
View file

@ -19,6 +19,7 @@ setup(
entry_points={"console_scripts": ["llama_cpp.server=llama_cpp.server:main"]}, entry_points={"console_scripts": ["llama_cpp.server=llama_cpp.server:main"]},
install_requires=[ install_requires=[
"typing-extensions>=4.5.0", "typing-extensions>=4.5.0",
"pydantic==1.10.7",
], ],
extras_require={ extras_require={
"server": ["uvicorn>=0.21.1", "fastapi>=0.95.0", "sse-starlette>=1.3.3"], "server": ["uvicorn>=0.21.1", "fastapi>=0.95.0", "sse-starlette>=1.3.3"],