feat(docker): install llama-cpp-python directly with OpenBLAS

Dockerfile

@@ -1,63 +1,51 @@
-FROM python:3.12-alpine
+FROM python:3.12-slim-bookworm
 
-# Ustaw katalog roboczy
 WORKDIR /app
 
-# Podstawowe zależności systemowe potrzebne do ML i audio
-RUN apk add --no-cache \
-    bash \
-    curl \
-    wget \
-    git \
-    build-base \
+# Install essential system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
     gcc \
     g++ \
-    make \
     cmake \
-    musl-dev \
-    linux-headers \
-    libstdc++ \
-    libgcc \
-    libffi-dev \
-    openblas-dev \
-    lapack-dev \
-    freetype-dev \
-    libpng-dev \
-    espeak-ng \
+    git \
+    git-lfs \
+    wget \
+    curl \
     sox \
     ffmpeg \
-    bash-completion \
-    zlib-dev \
-    xz-dev \
-    tiff-dev \
-    jpeg-dev \
+    espeak-ng \
+    libffi-dev \
+    libopenblas-dev \
+    liblapack-dev \
+    libfreetype6-dev \
+    libpng-dev \
+    zlib1g-dev \
+    libbz2-dev \
+    libjpeg-dev \
     gfortran \
-    pkgconfig \
-    curl-dev \
-    openssl-dev \
-    bzip2-dev \
-    xz-dev \
-    git-lfs \
-    && rm -rf /var/cache/apk/*
+    pkg-config \
+    bash-completion \
+    && rm -rf /var/lib/apt/lists/*
 
-# Skopiuj plik z wymaganiami
+# Copy Python requirements
 COPY requirements.txt /app/requirements.txt
 
 # Upgrade pip
 RUN pip install --upgrade pip setuptools wheel
 
-# Zainstaluj prebuilt wheel llama-cpp-python dla Alpine
-RUN pip install --no-cache-dir \
-    https://github.com/abetlen/llama-cpp-python/releases/download/v0.3.2/llama_cpp_python-0.3.2-cp312-cp312-linux_x86_64.whl
-
-# Instalacja zależności z requirements
+# Install dependencies from requirements
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Skopiuj resztę aplikacji
+# Build and install llama-cpp-python with OpenBLAS
+ENV CMAKE_ARGS="-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS"
+RUN pip install --no-cache-dir llama-cpp-python
+
+# Copy the rest of the application
 COPY . /app
 
-# Ustaw port
+# Expose port
 EXPOSE 7860
 
-# Uruchomienie aplikacji FastAPI przez Gunicorn
+# Run FastAPI with Gunicorn
 CMD ["gunicorn", "app.main:app", "-k", "uvicorn.workers.UvicornWorker", "--bind", "0.0.0.0:7860", "--workers", "1", "--timeout", "120"]

requirements.txt

@@ -1,6 +1,7 @@
 absl-py==2.1.0
 accelerate==1.5.2
 addict==2.4.0
+aiohappyeyeballs==2.6.1
 aiohttp==3.11.13
 aiosignal==1.3.2
 annotated-types==0.7.0
@@ -20,15 +21,20 @@ cloudpathlib==0.21.0
 colorama==0.4.6
 confection==0.1.5
 csvw==3.5.1
+curated-tokenizers==0.0.9
+curated-transformers==0.1.1
 cymem==2.0.11
 datasets==3.4.0
 decorator==5.2.1
 dill==0.3.8
 diskcache==5.6.3
+Distance==0.1.3
+dlinfo==2.0.0
 dnspython==2.7.0
+docopt==0.6.2
 email_validator==2.2.0
-en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl
-espeakng-loader==0.1.51.0
+en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl#sha256=1932429db727d4bff3deed6b34cfc05df17794f4a52eeb26cf8928f7c1a0fb85
+espeakng-loader==0.2.4
 executing==2.2.0
 fastapi==0.115.11
 fastapi-cli==0.0.7
@@ -50,6 +56,7 @@ huggingface-hub==0.29.3
 idna==3.10
 inflect==7.5.0
 ipython==9.0.2
+ipython_pygments_lexers==1.1.1
 isodate==0.7.2
 itsdangerous==2.2.0
 jedi==0.19.2
@@ -61,7 +68,9 @@ keras==3.9.0
 kokoro==0.9.4
 langcodes==3.5.0
 language-tags==1.2.0
+language_data==1.3.0
 lazy_loader==0.4
+libclang==18.1.1
 librosa==0.11.0
 llvmlite==0.44.0
 loguru==0.7.3
@@ -70,30 +79,58 @@ Markdown==3.7
 markdown-it-py==3.0.0
 MarkupSafe==3.0.2
 matplotlib-inline==0.1.7
+mdurl==0.1.2
+misaki==0.9.4
 ml_dtypes==0.5.1
 more-itertools==10.6.0
 mpmath==1.3.0
 msgpack==1.1.0
 multidict==6.1.0
+multiprocess==0.70.16
+murmurhash==1.0.12
+namex==0.0.8
 networkx==3.4.2
 nltk==3.9.1
 num2words==0.5.14
 numba==0.61.0
-numpy==1.25.2
+numpy==1.26.4
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-runtime-cu12==12.4.127
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.2.1.3
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-cusparselt-cu12==0.6.2
+nvidia-nccl-cu12==2.21.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.4.127
 opt_einsum==3.4.0
+optree==0.14.1
 orjson==3.10.15
 packaging==24.2
 pandas==2.2.3
+parso==0.8.4
 pexpect==4.9.0
 phonemizer-fork==3.3.2
 platformdirs==4.3.6
 pooch==1.8.2
 preshed==3.0.9
 prompt_toolkit==3.0.50
+propcache==0.3.0
 protobuf==5.29.3
 psutil==7.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+py-cpuinfo==9.0.0
+pyarrow==19.0.1
 pycparser==2.22
 pydantic==2.10.6
+pydantic-extra-types==2.10.3
+pydantic-settings==2.8.1
+pydantic_core==2.27.2
 Pygments==2.19.1
 pyparsing==3.2.1
 python-dateutil==2.9.0.post0
@@ -101,26 +138,38 @@ python-dotenv==1.0.1
 python-multipart==0.0.20
 pytz==2025.1
 PyYAML==6.0.2
+rdflib==7.1.3
+referencing==0.36.2
 regex==2024.11.6
 requests==2.32.3
+rfc3986==1.5.0
 rich==13.9.4
+rich-toolkit==0.13.2
+rpds-py==0.23.1
 sacremoses==0.1.1
+safetensors==0.5.3
 scikit-learn==1.6.1
-scipy==1.10.1
+scipy==1.15.2
+segments==2.3.0
 sentencepiece==0.2.0
 setuptools==76.0.0
+shellingham==1.5.4
 six==1.17.0
+smart-open==7.1.0
+sniffio==1.3.1
 soundfile==0.13.1
 soxr==0.5.0.post1
 spacy==3.8.4
 spacy-curated-transformers==0.3.0
 spacy-legacy==3.0.12
+spacy-loggers==1.0.5
 srsly==2.5.1
+stack-data==0.6.3
 starlette==0.46.1
 sympy==1.13.1
 tensorboard==2.19.0
 tensorboard-data-server==0.7.2
-tensorflow-cpu==2.19.0
+tensorflow==2.19.0
 termcolor==2.5.0
 thinc==8.3.4
 threadpoolctl==3.6.0
@@ -128,20 +177,25 @@ tokenizers==0.21.1
 torch==2.6.0
 torchaudio==2.6.0
 tqdm==4.67.1
+traitlets==5.14.3
 transformers==4.49.0
+triton==3.2.0
+typeguard==4.4.2
+typer==0.15.2
 typing_extensions==4.12.2
 tzdata==2025.1
 ujson==5.10.0
+uritemplate==4.1.1
 urllib3==2.3.0
 uvicorn==0.34.0
 uvloop==0.21.0
 wasabi==1.1.3
 watchfiles==1.0.4
 wcwidth==0.2.13
+weasel==0.4.1
 websockets==15.0.1
 Werkzeug==3.1.3
 wheel==0.45.1
 wrapt==1.17.2
 xxhash==3.5.0
 yarl==1.18.3
-