From 53f9862383aad7d081ef1bf2504c151f4cb87425 Mon Sep 17 00:00:00 2001 From: Olivier DEBAUCHE Date: Sun, 4 Feb 2024 21:08:52 +0100 Subject: [PATCH 1/3] Update dev.sh --- scripts/dev.sh | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/scripts/dev.sh b/scripts/dev.sh index 1c0c8e7a8a5..d1d750fca06 100755 --- a/scripts/dev.sh +++ b/scripts/dev.sh @@ -24,9 +24,15 @@ detect_cpu_features() { if [ "$cpu_arch" = "aarch64" ]; then pip_command="python -m pip install -v llama-cpp-python==$LLAMA_PYTHON_VERSION --only-binary=:all: --extra-index-url=https://gaby.github.io/arm64-wheels/" else - # Use @jllllll provided wheels + # Use @smartappli provided wheels cpu_feature=$(detect_cpu_features) - pip_command="python -m pip install -v llama-cpp-python==$LLAMA_PYTHON_VERSION --only-binary=:all: --extra-index-url=https://jllllll.github.io/llama-cpp-python-cuBLAS-wheels/$cpu_feature/cpu" + if [ "$SERGE_GPU_NVIDIA_SUPPORT" = true ]; then + pip_command="python -m pip install -v llama-cpp-python==$LLAMA_PYTHON_VERSION --only-binary=:all: --extra-index-url=https://smartappli.github.io/llama-cpp-python-cuBLAS-wheels/$cpu_feature/cu122" + elif [ "$SERGE_GPU_AMD_SUPPORT" = true ]; then + pip_command="python -m pip install -v llama-cpp-python==$LLAMA_PYTHON_VERSION --only-binary=:all: --extra-index-url=https://smartappli.github.io/llama-cpp-python-cuBLAS-wheels/$cpu_feature/rocm5.6.1" + else + pip_command="python -m pip install -v llama-cpp-python==$LLAMA_PYTHON_VERSION --only-binary=:all: --extra-index-url=https://smartappli.github.io/llama-cpp-python-cuBLAS-wheels/$cpu_feature/cpu" + fi fi echo "Recommended install command for llama-cpp-python: $pip_command" From dd278f05e300cf93abf80f076ad6c2b7e29645f1 Mon Sep 17 00:00:00 2001 From: Olivier DEBAUCHE Date: Sun, 4 Feb 2024 21:10:27 +0100 Subject: [PATCH 2/3] Update deploy.sh --- scripts/deploy.sh | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/scripts/deploy.sh b/scripts/deploy.sh index d134e48cda6..938d694c32c 100755 --- a/scripts/deploy.sh +++ b/scripts/deploy.sh @@ -19,14 +19,19 @@ detect_cpu_features() { echo "basic" fi } - # Check if the CPU architecture is aarch64/arm64 if [ "$cpu_arch" = "aarch64" ]; then pip_command="python -m pip install -v llama-cpp-python==$LLAMA_PYTHON_VERSION --only-binary=:all: --extra-index-url=https://gaby.github.io/arm64-wheels/" else - # Use @jllllll provided wheels + # Use @smartappli provided wheels cpu_feature=$(detect_cpu_features) - pip_command="python -m pip install -v llama-cpp-python==$LLAMA_PYTHON_VERSION --only-binary=:all: --extra-index-url=https://jllllll.github.io/llama-cpp-python-cuBLAS-wheels/$cpu_feature/cpu" + if [ "$SERGE_GPU_NVIDIA_SUPPORT" = true ]; then + pip_command="python -m pip install -v llama-cpp-python==$LLAMA_PYTHON_VERSION --only-binary=:all: --extra-index-url=https://smartappli.github.io/llama-cpp-python-cuBLAS-wheels/$cpu_feature/cu122" + elif [ "$SERGE_GPU_AMD_SUPPORT" = true ]; then + pip_command="python -m pip install -v llama-cpp-python==$LLAMA_PYTHON_VERSION --only-binary=:all: --extra-index-url=https://smartappli.github.io/llama-cpp-python-cuBLAS-wheels/$cpu_feature/rocm5.6.1" + else + pip_command="python -m pip install -v llama-cpp-python==$LLAMA_PYTHON_VERSION --only-binary=:all: --extra-index-url=https://smartappli.github.io/llama-cpp-python-cuBLAS-wheels/$cpu_feature/cpu" + fi fi echo "Recommended install command for llama-cpp-python: $pip_command" From 128e76c534f01ee838b38670be2095f20c373b9e Mon Sep 17 00:00:00 2001 From: Olivier DEBAUCHE Date: Sun, 4 Feb 2024 21:12:09 +0100 Subject: [PATCH 3/3] Update serge.env --- scripts/serge.env | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/scripts/serge.env b/scripts/serge.env index 82bdec3a769..d3cf5672d53 100644 --- a/scripts/serge.env +++ b/scripts/serge.env @@ -1,2 +1,4 @@ -LLAMA_PYTHON_VERSION=0.2.26 +LLAMA_PYTHON_VERSION=0.2.38 +SERGE_GPU_NVIDIA_SUPPORT=false +SERGE_GPU_AMD_SUPPORT=false SERGE_ENABLE_IPV6=false