Merge pull request #19 from pitangainnovare/feat/avx-disable-option

Inclui possibilidade de desativar instruções AVX

Author: pitangainnovare

compose/local/django/Dockerfile

@@ -30,10 +30,12 @@ RUN apt-get update && \
 # Instalar ninja-build y cmake
 RUN apt-get install -y ninja-build cmake
 
-# Configurar variables de entorno para compilar con BLAS y SIMD
-ENV CFLAGS="-mfma -mavx2" \
-    CXXFLAGS="-mfma -mavx2" \
-    CMAKE_ARGS="-DGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS"
+# Configurar variables de entorno para compilar con BLAS y SIMD condicionalmente
+ARG ENABLE_OPTIMIZATIONS=true
+ARG ENABLE_OPTIMIZATIONS=true
+ENV CFLAGS="${ENABLE_OPTIMIZATIONS:+-mfma -mavx2}" \
+    CXXFLAGS="${ENABLE_OPTIMIZATIONS:+-mfma -mavx2}" \
+    CMAKE_ARGS="${ENABLE_OPTIMIZATIONS:+-DGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS}"
 
 # Actualizar pip, setuptools y wheel antes de instalar dependencias
 RUN python -m pip install --upgrade pip setuptools wheel
@@ -42,13 +44,12 @@ RUN python -m pip install --upgrade pip setuptools wheel
 COPY ./requirements .
 
 # Update pip
-#RUN python -m pip install --upgrade pip
+RUN python -m pip install --upgrade pip
 
 # Create Python Dependency and Sub-Dependency Wheels.
 RUN pip wheel --wheel-dir /usr/src/app/wheels  \
   -r ${BUILD_ENVIRONMENT}.txt
 
-
 # Python 'run' stage
 FROM python AS python-run-stage
 
@@ -59,6 +60,12 @@ ENV PYTHONUNBUFFERED 1
 ENV PYTHONDONTWRITEBYTECODE 1
 ENV BUILD_ENV ${BUILD_ENVIRONMENT}
 
+# Disable AVX support for llama-cpp-python if needed
+ARG DISABLE_AVX=false
+
+# Set the version of llama-cpp-python
+ARG LLAMA_VERSION=0.3.14
+
 WORKDIR ${APP_HOME}
 
 # Install required system dependencies
@@ -75,10 +82,17 @@ RUN apt-get update && apt-get install --no-install-recommends -y \
 # copy python dependency wheels from python-build-stage
 COPY --from=python-build-stage /usr/src/app/wheels  /wheels/
 
-# use wheels to install python dependencies
-RUN pip install --no-cache-dir --no-index --find-links=/wheels/ /wheels/* \
+# Use wheels to install python dependencies (excluding llama-cpp-python)
+RUN pip install --no-cache-dir --no-index --find-links=/wheels/ $(find /wheels/ -name "*.whl" ! -name "llama_cpp_python*") \
 	&& rm -rf /wheels/
 
+# Install llama-cpp-python with specific CMAKE flags for Kubernetes nodes with or without AVX support
+RUN if [ "${DISABLE_AVX}" = "true" ]; then \
+  CMAKE_ARGS='-DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DLLAMA_F16C=OFF -DLLAMA_OPENMP=ON' pip install llama-cpp-python==${LLAMA_VERSION} --force-reinstall --no-cache-dir; \
+    else \
+  pip install llama-cpp-python==${LLAMA_VERSION} --force-reinstall --no-cache-dir; \
+    fi
+
 COPY ./compose/production/django/entrypoint /entrypoint
 RUN sed -i 's/\r$//g' /entrypoint
 RUN chmod +x /entrypoint
@@ -87,7 +101,6 @@ COPY ./compose/local/django/start /start
 RUN sed -i 's/\r$//g' /start
 RUN chmod +x /start
 
-
 COPY ./compose/local/django/celery/worker/start /start-celeryworker
 RUN sed -i 's/\r$//g' /start-celeryworker
 RUN chmod +x /start-celeryworker
@@ -100,7 +113,6 @@ COPY ./compose/local/django/celery/flower/start /start-flower
 RUN sed -i 's/\r$//g' /start-flower
 RUN chmod +x /start-flower
 
-
 # copy application code to WORKDIR
 COPY . ${APP_HOME}
 

compose/production/django/Dockerfile

@@ -26,7 +26,6 @@ RUN python -m pip install --upgrade pip
 RUN pip wheel --wheel-dir /usr/src/app/wheels  \
   -r ${BUILD_ENVIRONMENT}.txt
 
-
 # Python 'run' stage
 FROM python as python-run-stage
 
@@ -37,12 +36,17 @@ ENV PYTHONUNBUFFERED 1
 ENV PYTHONDONTWRITEBYTECODE 1
 ENV BUILD_ENV ${BUILD_ENVIRONMENT}
 
+# Install llama-cpp-python with specific CMAKE flags for Kubernetes nodes without AVX support
+ARG DISABLE_AVX=true
+
+# Set the version of llama-cpp-python
+ARG LLAMA_VERSION=0.3.14
+
 WORKDIR ${APP_HOME}
 
 RUN addgroup --system django \
     && adduser --system --ingroup django django
 
-
 # Install required system dependencies
 RUN apt-get update && apt-get install --no-install-recommends -y \
   # psycopg2 dependencies
@@ -57,34 +61,36 @@ RUN apt-get update && apt-get install --no-install-recommends -y \
 # copy python dependency wheels from python-build-stage
 COPY --from=python-build-stage /usr/src/app/wheels  /wheels/
 
-# use wheels to install python dependencies
-RUN pip install --no-cache-dir --no-index --find-links=/wheels/ /wheels/* \
-  && rm -rf /wheels/
+# use wheels to install python dependencies (excluding llama-cpp-python)
+RUN pip install --no-cache-dir --no-index --find-links=/wheels/ $(find /wheels/ -name "*.whl" ! -name "llama_cpp_python*") && rm -rf /wheels/
 
+# Install llama-cpp-python with specific CMAKE flags for Kubernetes nodes without AVX support
+RUN if [ "${DISABLE_AVX}" = "true" ]; then \
+  CMAKE_ARGS='-DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DLLAMA_F16C=OFF -DLLAMA_OPENMP=ON' pip install llama-cpp-python==${LLAMA_VERSION} --force-reinstall --no-cache-dir; \
+    else \
+  pip install llama-cpp-python==${LLAMA_VERSION} --force-reinstall --no-cache-dir; \
+    fi
 
 COPY --chown=django:django ./compose/production/django/entrypoint /entrypoint
 RUN sed -i 's/\r$//g' /entrypoint
 RUN chmod +x /entrypoint
 
-
 COPY --chown=django:django ./compose/production/django/start /start
 RUN sed -i 's/\r$//g' /start
 RUN chmod +x /start
+
 COPY --chown=django:django ./compose/production/django/celery/worker/start /start-celeryworker
 RUN sed -i 's/\r$//g' /start-celeryworker
 RUN chmod +x /start-celeryworker
 
-
 COPY --chown=django:django ./compose/production/django/celery/beat/start /start-celerybeat
 RUN sed -i 's/\r$//g' /start-celerybeat
 RUN chmod +x /start-celerybeat
 
-
 COPY ./compose/production/django/celery/flower/start /start-flower
 RUN sed -i 's/\r$//g' /start-flower
 RUN chmod +x /start-flower
 
-
 # copy application code to WORKDIR
 COPY --chown=django:django . ${APP_HOME}
 

requirements/base.txt

@@ -40,4 +40,4 @@ whitenoise==6.6.0  # https://github.com/evansd/whitenoise
 # Llama
 # ------------------------------------------------------------------------------
 huggingface-hub==0.26.1
-llama-cpp-python==0.3.1
+llama-cpp-python==0.3.14