Files
ollama37/docs/linux.mdx
Shang Chieh Tseng ef14fb5b26 Sync with upstream ollama/ollama and restore Tesla K80 (compute 3.7) support
This commit represents a complete rework after pulling the latest changes from
official ollama/ollama repository and re-applying Tesla K80 compatibility patches.

## Key Changes

### CUDA Compute Capability 3.7 Support (Tesla K80)
- Added sm_37 (compute 3.7) to CMAKE_CUDA_ARCHITECTURES in CMakeLists.txt
- Updated CMakePresets.json to include compute 3.7 in "CUDA 11" preset
- Using 37-virtual (PTX with JIT compilation) for maximum compatibility

### Legacy Toolchain Compatibility
- **NVIDIA Driver**: 470.256.02 (last version supporting Kepler/K80)
- **CUDA Version**: 11.4.4 (last CUDA 11.x supporting compute 3.7)
- **GCC Version**: 10.5.0 (required by CUDA 11.4 host_config.h)

### CPU Architecture Trade-offs
Due to GCC 10.5 limitation, sacrificed newer CPU optimizations:
- Alderlake CPU variant enabled WITHOUT AVX_VNNI (requires GCC 11+)
- Still supports: SSE4.2, AVX, F16C, AVX2, BMI2, FMA
- Performance impact: ~3-7% on newer CPUs (acceptable for K80 compatibility)

### Build System Updates
- Modified ml/backend/ggml/ggml/src/ggml-cuda/CMakeLists.txt for compute 3.7
- Added -Wno-deprecated-gpu-targets flag to suppress warnings
- Updated ml/backend/ggml/ggml/src/CMakeLists.txt for Alderlake without AVX_VNNI

### Upstream Sync
Merged latest llama.cpp changes including:
- Enhanced KV cache management with ISWA and hybrid memory support
- Improved multi-modal support (mtmd framework)
- New model architectures (Gemma3, Llama4, Qwen3, etc.)
- GPU backend improvements for CUDA, Metal, and ROCm
- Updated quantization support and GGUF format handling

### Documentation
- Updated CLAUDE.md with comprehensive build instructions
- Documented toolchain constraints and CPU architecture trade-offs
- Removed outdated CI/CD workflows (tesla-k80-*.yml)
- Cleaned up temporary development artifacts

## Rationale

This fork maintains Tesla K80 GPU support (compute 3.7) which was dropped in
official Ollama due to legacy driver/CUDA requirements. The toolchain constraint
creates a deadlock:
- K80 → Driver 470 → CUDA 11.4 → GCC 10 → No AVX_VNNI

We accept the loss of cutting-edge CPU optimizations to enable running modern
LLMs on legacy but still capable Tesla K80 hardware (12GB VRAM per GPU).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-05 14:03:05 +08:00

200 lines
4.0 KiB
Plaintext

---
title: Linux
---
## Install
To install Ollama, run the following command:
```shell
curl -fsSL https://ollama.com/install.sh | sh
```
## Manual install
<Note>
If you are upgrading from a prior version, you should remove the old libraries
with `sudo rm -rf /usr/lib/ollama` first.
</Note>
Download and extract the package:
```shell
curl -fsSL https://ollama.com/download/ollama-linux-amd64.tgz \
| sudo tar zx -C /usr
```
Start Ollama:
```shell
ollama serve
```
In another terminal, verify that Ollama is running:
```shell
ollama -v
```
### AMD GPU install
If you have an AMD GPU, also download and extract the additional ROCm package:
```shell
curl -fsSL https://ollama.com/download/ollama-linux-amd64-rocm.tgz \
| sudo tar zx -C /usr
```
### ARM64 install
Download and extract the ARM64-specific package:
```shell
curl -fsSL https://ollama.com/download/ollama-linux-arm64.tgz \
| sudo tar zx -C /usr
```
### Adding Ollama as a startup service (recommended)
Create a user and group for Ollama:
```shell
sudo useradd -r -s /bin/false -U -m -d /usr/share/ollama ollama
sudo usermod -a -G ollama $(whoami)
```
Create a service file in `/etc/systemd/system/ollama.service`:
```ini
[Unit]
Description=Ollama Service
After=network-online.target
[Service]
ExecStart=/usr/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=$PATH"
[Install]
WantedBy=multi-user.target
```
Then start the service:
```shell
sudo systemctl daemon-reload
sudo systemctl enable ollama
```
### Install CUDA drivers (optional)
[Download and install](https://developer.nvidia.com/cuda-downloads) CUDA.
Verify that the drivers are installed by running the following command, which should print details about your GPU:
```shell
nvidia-smi
```
### Install AMD ROCm drivers (optional)
[Download and Install](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/tutorial/quick-start.html) ROCm v6.
### Start Ollama
Start Ollama and verify it is running:
```shell
sudo systemctl start ollama
sudo systemctl status ollama
```
<Note>
While AMD has contributed the `amdgpu` driver upstream to the official linux
kernel source, the version is older and may not support all ROCm features. We
recommend you install the latest driver from
https://www.amd.com/en/support/linux-drivers for best support of your Radeon
GPU.
</Note>
## Customizing
To customize the installation of Ollama, you can edit the systemd service file or the environment variables by running:
```shell
sudo systemctl edit ollama
```
Alternatively, create an override file manually in `/etc/systemd/system/ollama.service.d/override.conf`:
```ini
[Service]
Environment="OLLAMA_DEBUG=1"
```
## Updating
Update Ollama by running the install script again:
```shell
curl -fsSL https://ollama.com/install.sh | sh
```
Or by re-downloading Ollama:
```shell
curl -fsSL https://ollama.com/download/ollama-linux-amd64.tgz \
| sudo tar zx -C /usr
```
## Installing specific versions
Use `OLLAMA_VERSION` environment variable with the install script to install a specific version of Ollama, including pre-releases. You can find the version numbers in the [releases page](https://github.com/ollama/ollama/releases).
For example:
```shell
curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.5.7 sh
```
## Viewing logs
To view logs of Ollama running as a startup service, run:
```shell
journalctl -e -u ollama
```
## Uninstall
Remove the ollama service:
```shell
sudo systemctl stop ollama
sudo systemctl disable ollama
sudo rm /etc/systemd/system/ollama.service
```
Remove ollama libraries from your lib directory (either `/usr/local/lib`, `/usr/lib`, or `/lib`):
```shell
sudo rm -r $(which ollama | tr 'bin' 'lib')
```
Remove the ollama binary from your bin directory (either `/usr/local/bin`, `/usr/bin`, or `/bin`):
```shell
sudo rm $(which ollama)
```
Remove the downloaded models and Ollama service user and group:
```shell
sudo userdel ollama
sudo groupdel ollama
sudo rm -r /usr/share/ollama
```