Frank
02883d3ed2
Copy of the legacy ~/.pi/agent/docs tree rebuilt as the command-center knowledge base: concept files promoted to path identity, index listings stripped of frontmatter, all wikilinks/relative links resolved, every checkable claim verified against the live fleet (Dankserver = Ryzen 7 7700X + RTX 3090; Strix Halo is Dankclaw), unverifiable claims tagged. kb-lint exits 0.
1.6 KiB
1.6 KiB
type, title, description, tags, timestamp, verified
| type | title | description | tags | timestamp | verified | ||||
|---|---|---|---|---|---|---|---|---|---|
| howto | Troubleshooting Ornith + llama.cpp | Common errors — CUDA OOM, segfaults, model not responding, poor performance — and their fixes. |
|
2026-07-18 | 2026-08-28 |
Troubleshooting
CUDA Out of Memory
Error: cudaMalloc failed: out of memory
Solution: Reduce -ngl value to offload fewer layers to GPU.
Segmentation Fault
Segmentation fault (core dumped)
Solution:
- Reduce context size (
-cparameter) - Reduce GPU layers (
-ngl) - Check if model file is corrupted
Model Not Responding
curl: (7) Failed to connect to localhost port 8080
Solution: Check if server is running:
ps aux | grep llama-server
tail -f ~/logs/llama-server.log
Poor Performance
Solutions:
- Increase GPU layers (
-ngl) - Enable Flash Attention:
--flash-attn on(if supported) - Use a smaller quantization (Q4_K_M instead of Q8_0)
- Reduce context window size
Security Considerations
- Local Server: By default, binds to localhost (127.0.0.1)
- Network Exposure: If binding to 0.0.0.0, consider:
- Adding authentication (
--api-key) - Using a firewall to restrict access
- Running behind a reverse proxy with TLS
- Adding authentication (
# Add API key authentication
./build/bin/llama-server ... --api-key your-secret-key
Related
- Installation — The commands that might be causing issues
- GPU Offloading — GPU configuration