matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-18 11:47:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update TC-RUNTIME-002 to handle UVM device workaround

Browse Source 
- Add step to check/create /dev/nvidia-uvm device files
- Use nvidia-modprobe -u -c=0 if UVM devices missing
- Restart container after creating UVM devices
- Update criteria to clarify GPU detection requirements
- Increase timeout to 120s for container restart

Fixes issue where nvidia-smi works but Ollama only detects CPU.

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Shang Chieh Tseng
2025-12-15 19:58:16 +08:00
parent 23c92954d7
commit 8d65fd4211
1 changed files with 23 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
tests/testcases/runtime/TC-RUNTIME-002.yml
View File

@@ -2,7 +2,7 @@ id: TC-RUNTIME-002
name: GPU Detection name: GPU Detection
suite: runtime suite: runtime
priority: 2 priority: 2
timeout: 60000 timeout: 120000
dependencies: dependencies:
- TC-RUNTIME-001 - TC-RUNTIME-001
@@ -14,16 +14,32 @@ steps:
- name: Check CUDA libraries - name: Check CUDA libraries
command: docker exec ollama37 ldconfig -p | grep -i cuda | head -5 command: docker exec ollama37 ldconfig -p | grep -i cuda | head -5
- name: Check Ollama GPU detection - name: Check UVM device files (create if missing)
command: cd docker && docker compose logs 2>&1 | grep -i gpu | head -10 command: |
if [ ! -e /dev/nvidia-uvm ]; then
echo "UVM device missing, creating with nvidia-modprobe..."
sudo nvidia-modprobe -u -c=0
echo "Restarting container to pick up UVM devices..."
cd docker && docker compose restart
sleep 15
else
echo "UVM device exists: $(ls -l /dev/nvidia-uvm)"
fi
- name: Check Ollama GPU detection in logs
command: |
cd docker && docker compose logs 2>&1 | grep -E "(inference compute|GPU detected)" | tail -5
criteria: | criteria: |
Tesla K80 GPU should be detected inside the container. Tesla K80 GPU should be detected by both nvidia-smi AND Ollama CUDA runtime.
Expected: Expected:
- nvidia-smi shows Tesla K80 GPU(s) - nvidia-smi shows Tesla K80 GPU(s) with Driver 470.x
- Driver version 470.x (or compatible)
- CUDA libraries are available (libcuda, libcublas, etc.) - CUDA libraries are available (libcuda, libcublas, etc.)
- Ollama logs mention GPU detection - /dev/nvidia-uvm device file exists (required for CUDA runtime)
- Ollama logs show GPU detection, NOT "id=cpu library=cpu"
NOTE: If nvidia-smi works but Ollama shows only CPU, the UVM device
files are missing. The test will auto-fix with nvidia-modprobe -u -c=0.
The K80 has 12GB VRAM per GPU. Accept variations in reported memory. The K80 has 12GB VRAM per GPU. Accept variations in reported memory.