matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-09 23:37:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Shang Chieh Tseng
2025-11-13 18:14:16 +08:00
parent 68f9b1580e
commit b5dac79d2c
1 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
docker/README.md
View File

@@ -26,7 +26,7 @@ The runtime uses the builder image as its base to ensure library path compatibil
- NVIDIA GPU drivers (470+ for Tesla K80) - NVIDIA GPU drivers (470+ for Tesla K80)
- Verify GPU access: - Verify GPU access:
```bash ```bash
docker run --rm --runtime=nvidia --gpus all nvidia/cuda:11.4.3-base-rockylinux8 nvidia-smi docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi
``` ```
## Quick Start ## Quick Start
@@ -49,17 +49,17 @@ This will:
### 2. Run with Docker Compose (Recommended) ### 2. Run with Docker Compose (Recommended)
```bash ```bash
docker-compose up -d docker compose up -d
``` ```
Check logs: Check logs:
```bash ```bash
docker-compose logs -f docker compose logs -f
``` ```
Stop the server: Stop the server:
```bash ```bash
docker-compose down docker compose down
``` ```
### 3. Run Manually ### 3. Run Manually
@@ -212,19 +212,19 @@ docker build -f runtime/Dockerfile -t ollama37:latest .
```bash ```bash
# Start server # Start server
docker-compose up -d docker compose up -d
# View logs (live tail) # View logs (live tail)
docker-compose logs -f docker compose logs -f
# Stop server # Stop server
docker-compose down docker compose down
# Stop and remove volumes # Stop and remove volumes
docker-compose down -v docker compose down -v
# Restart server # Restart server
docker-compose restart docker compose restart
``` ```
### Manual Docker Commands ### Manual Docker Commands
@@ -364,7 +364,7 @@ This creates the required device files:
Then restart the container: Then restart the container:
```bash ```bash
docker-compose restart docker compose restart
``` ```
**Result:** GPUs now properly detected by CUDA runtime. **Result:** GPUs now properly detected by CUDA runtime.
@@ -376,7 +376,7 @@ docker-compose restart
ls -l /dev/nvidia-uvm* ls -l /dev/nvidia-uvm*
# Check Ollama logs for GPU detection # Check Ollama logs for GPU detection
docker-compose logs | grep -i gpu docker compose logs | grep -i gpu
# You should see output like: # You should see output like:
# ollama37 | time=... level=INFO msg="Nvidia GPU detected" name="Tesla K80" vram=11441 MiB # ollama37 | time=... level=INFO msg="Nvidia GPU detected" name="Tesla K80" vram=11441 MiB
@@ -445,14 +445,14 @@ make build
make build-runtime make build-runtime
# Restart container # Restart container
docker-compose restart docker compose restart
``` ```
### Rebuild everything from scratch ### Rebuild everything from scratch
```bash ```bash
# Stop and remove containers # Stop and remove containers
docker-compose down -v docker compose down -v
# Remove images # Remove images
make clean make clean
@@ -461,7 +461,7 @@ make clean
make build make build
# Start fresh # Start fresh
docker-compose up -d docker compose up -d
``` ```
### Rebuild only builder (rare) ### Rebuild only builder (rare)
@@ -489,8 +489,8 @@ make build-runtime
make build make build
# Run and test # Run and test
docker-compose up -d docker compose up -d
docker-compose logs -f docker compose logs -f
# If issues, check inside container # If issues, check inside container
docker exec -it ollama37 bash docker exec -it ollama37 bash