Merge branch 'main' of github.com:abetlen/llama_cpp_python into main

Author: abetlen

README.md

@@ -169,7 +169,7 @@ docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/ggm
 ## Low-level API
 
 The low-level API is a direct [`ctypes`](https://docs.python.org/3/library/ctypes.html) binding to the C API provided by `llama.cpp`.
-The entire lowe-level API can be found in [llama_cpp/llama_cpp.py](https://github.com/abetlen/llama-cpp-python/blob/master/llama_cpp/llama_cpp.py) and directly mirrors the C API in [llama.h](https://github.com/ggerganov/llama.cpp/blob/master/llama.h).
+The entire low-level API can be found in [llama_cpp/llama_cpp.py](https://github.com/abetlen/llama-cpp-python/blob/master/llama_cpp/llama_cpp.py) and directly mirrors the C API in [llama.h](https://github.com/ggerganov/llama.cpp/blob/master/llama.h).
 
 Below is a short example demonstrating how to use the low-level API to tokenize a prompt:
 

docker/openblas_simple/Dockerfile

@@ -9,7 +9,7 @@ COPY . .
 RUN apt update && apt install -y libopenblas-dev ninja-build build-essential
 RUN python -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings
 
-RUN LLAMA_OPENBLAS=1 pip install llama_cpp_python --verbose
+RUN CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama_cpp_python --verbose
 
 # Run the server
 CMD python3 -m llama_cpp.server

poetry.lock

@@ -17,17 +17,17 @@ python = "^3.8.1"
 typing-extensions = "^4.7.1"
 numpy = "^1.24.4"
 diskcache = "^5.6.1"
-uvicorn = { version = "^0.23.1", optional = true }
+uvicorn = { version = "^0.23.2", optional = true }
 fastapi = { version = ">=0.100.0", optional = true }
 sse-starlette = { version = ">=1.6.1", optional = true }
 pydantic-settings = { version = ">=2.0.1", optional = true }
 
 [tool.poetry.group.dev.dependencies]
 black = "^23.7.0"
 twine = "^4.0.2"
-mkdocs = "^1.4.3"
+mkdocs = "^1.5.2"
 mkdocstrings = {extras = ["python"], version = "^0.22.0"}
-mkdocs-material = "^9.1.19"
+mkdocs-material = "^9.1.21"
 pytest = "^7.4.0"
 httpx = "^0.24.1"
 scikit-build = "0.17.6"