line feed
This commit is contained in:
Michael Yang
parent
77ccbf04dc
commit
6a07344786
2 changed files with 83 additions and 83 deletions
142
docs/docker.md
142
docs/docker.md
|
|
@ -1,71 +1,71 @@
|
|||
# Ollama Docker image
|
||||
|
||||
### CPU only
|
||||
|
||||
```bash
|
||||
docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
|
||||
```
|
||||
|
||||
### Nvidia GPU
|
||||
Install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html#installation).
|
||||
|
||||
#### Install with Apt
|
||||
1. Configure the repository
|
||||
```bash
|
||||
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \
|
||||
| sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
|
||||
curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \
|
||||
| sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \
|
||||
| sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
|
||||
sudo apt-get update
|
||||
```
|
||||
2. Install the NVIDIA Container Toolkit packages
|
||||
```bash
|
||||
sudo apt-get install -y nvidia-container-toolkit
|
||||
```
|
||||
|
||||
#### Install with Yum or Dnf
|
||||
1. Configure the repository
|
||||
|
||||
```bash
|
||||
curl -s -L https://nvidia.github.io/libnvidia-container/stable/rpm/nvidia-container-toolkit.repo \
|
||||
| sudo tee /etc/yum.repos.d/nvidia-container-toolkit.repo
|
||||
```
|
||||
|
||||
2. Install the NVIDIA Container Toolkit packages
|
||||
|
||||
```bash
|
||||
sudo yum install -y nvidia-container-toolkit
|
||||
```
|
||||
|
||||
#### Configure Docker to use Nvidia driver
|
||||
```
|
||||
sudo nvidia-ctk runtime configure --runtime=docker
|
||||
sudo systemctl restart docker
|
||||
```
|
||||
|
||||
#### Start the container
|
||||
|
||||
```bash
|
||||
docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
|
||||
```
|
||||
|
||||
### AMD GPU
|
||||
|
||||
To run Ollama using Docker with AMD GPUs, use the `rocm` tag and the following command:
|
||||
|
||||
```
|
||||
docker run -d --device /dev/kfd --device /dev/dri -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama:rocm
|
||||
```
|
||||
|
||||
### Run model locally
|
||||
|
||||
Now you can run a model:
|
||||
|
||||
```
|
||||
docker exec -it ollama ollama run llama3.1
|
||||
```
|
||||
|
||||
### Try different models
|
||||
|
||||
More models can be found on the [Ollama library](https://ollama.com/library).
|
||||
# Ollama Docker image
|
||||
|
||||
### CPU only
|
||||
|
||||
```bash
|
||||
docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
|
||||
```
|
||||
|
||||
### Nvidia GPU
|
||||
Install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html#installation).
|
||||
|
||||
#### Install with Apt
|
||||
1. Configure the repository
|
||||
```bash
|
||||
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \
|
||||
| sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
|
||||
curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \
|
||||
| sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \
|
||||
| sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
|
||||
sudo apt-get update
|
||||
```
|
||||
2. Install the NVIDIA Container Toolkit packages
|
||||
```bash
|
||||
sudo apt-get install -y nvidia-container-toolkit
|
||||
```
|
||||
|
||||
#### Install with Yum or Dnf
|
||||
1. Configure the repository
|
||||
|
||||
```bash
|
||||
curl -s -L https://nvidia.github.io/libnvidia-container/stable/rpm/nvidia-container-toolkit.repo \
|
||||
| sudo tee /etc/yum.repos.d/nvidia-container-toolkit.repo
|
||||
```
|
||||
|
||||
2. Install the NVIDIA Container Toolkit packages
|
||||
|
||||
```bash
|
||||
sudo yum install -y nvidia-container-toolkit
|
||||
```
|
||||
|
||||
#### Configure Docker to use Nvidia driver
|
||||
```
|
||||
sudo nvidia-ctk runtime configure --runtime=docker
|
||||
sudo systemctl restart docker
|
||||
```
|
||||
|
||||
#### Start the container
|
||||
|
||||
```bash
|
||||
docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
|
||||
```
|
||||
|
||||
### AMD GPU
|
||||
|
||||
To run Ollama using Docker with AMD GPUs, use the `rocm` tag and the following command:
|
||||
|
||||
```
|
||||
docker run -d --device /dev/kfd --device /dev/dri -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama:rocm
|
||||
```
|
||||
|
||||
### Run model locally
|
||||
|
||||
Now you can run a model:
|
||||
|
||||
```
|
||||
docker exec -it ollama ollama run llama3.1
|
||||
```
|
||||
|
||||
### Try different models
|
||||
|
||||
More models can be found on the [Ollama library](https://ollama.com/library).
|
||||
|
|
|
|||
24
llm/ext_server/CMakeLists.txt
vendored
24
llm/ext_server/CMakeLists.txt
vendored
|
|
@ -1,13 +1,13 @@
|
|||
set(TARGET ollama_llama_server)
|
||||
option(LLAMA_SERVER_VERBOSE "Build verbose logging option for Server" ON)
|
||||
include_directories(${CMAKE_CURRENT_SOURCE_DIR})
|
||||
add_executable(${TARGET} server.cpp utils.hpp json.hpp httplib.h)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_compile_definitions(${TARGET} PRIVATE
|
||||
SERVER_VERBOSE=$<BOOL:${LLAMA_SERVER_VERBOSE}>
|
||||
)
|
||||
target_link_libraries(${TARGET} PRIVATE ggml llama common llava ${CMAKE_THREAD_LIBS_INIT})
|
||||
if (WIN32)
|
||||
TARGET_LINK_LIBRARIES(${TARGET} PRIVATE ws2_32)
|
||||
endif()
|
||||
set(TARGET ollama_llama_server)
|
||||
option(LLAMA_SERVER_VERBOSE "Build verbose logging option for Server" ON)
|
||||
include_directories(${CMAKE_CURRENT_SOURCE_DIR})
|
||||
add_executable(${TARGET} server.cpp utils.hpp json.hpp httplib.h)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_compile_definitions(${TARGET} PRIVATE
|
||||
SERVER_VERBOSE=$<BOOL:${LLAMA_SERVER_VERBOSE}>
|
||||
)
|
||||
target_link_libraries(${TARGET} PRIVATE ggml llama common llava ${CMAKE_THREAD_LIBS_INIT})
|
||||
if (WIN32)
|
||||
TARGET_LINK_LIBRARIES(${TARGET} PRIVATE ws2_32)
|
||||
endif()
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
Loading…
Reference in a new issue