ac2ec40657
Closes #1123. Implements all three phases of the local LLM standardization: PHASE 1 — Deployment: - docs/local-llm.md: full deployment guide (build, model download, health check, model path convention /opt/models/llama/, hardware recommendations) - systemd/llama-server.service: hardened unit with resource limits and auto-restart - Health check: /health endpoint + model loaded verification PHASE 2 — Hermes Integration: - bin/llama_client.py: OpenAI-compatible Python client wrapping llama.cpp HTTP API (chat completions, streaming, raw completions, health check, model listing, benchmarking, full CLI interface) - nexus/llama_provider.py: Hermes inference router provider adapter - Activates when external APIs fail, LOCAL_ONLY=true, or explicit local request - Response format normalized to OpenAI-compatible chat completions - Token usage estimated and logged - Health caching with TTL for efficiency PHASE 3 — Optimization & Ops: - Benchmarking: client.benchmark() + CLI benchmark command - Quantization guide: Q4_K_M recommended for fleet, Q6_K for high-RAM, Q3_K for low - Model recommendations for VPS Beta (3B), VPS Alpha (7B), Mac (7B Q6_K) - Night watch integration: health probe script with auto-restart Fleet standard model: Qwen2.5-7B-Instruct-Q4_K_M.gguf Default endpoint: http://localhost:11435 22 tests pass.
52 lines
1015 B
Desktop File
52 lines
1015 B
Desktop File
[Unit]
|
|
Description=llama.cpp Local LLM Server
|
|
After=network-online.target
|
|
Wants=network-online.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
User=root
|
|
Group=root
|
|
|
|
# Model and server configuration
|
|
Environment=MODEL_PATH=/opt/models/llama/Qwen2.5-7B-Instruct-Q4_K_M.gguf
|
|
Environment=LLAMA_HOST=0.0.0.0
|
|
Environment=LLAMA_PORT=11435
|
|
Environment=LLAMA_CTX_SIZE=4096
|
|
Environment=LLAMA_THREADS=4
|
|
|
|
ExecStart=/usr/local/bin/llama-server \
|
|
-m ${MODEL_PATH} \
|
|
--host ${LLAMA_HOST} \
|
|
--port ${LLAMA_PORT} \
|
|
-c ${LLAMA_CTX_SIZE} \
|
|
-t ${LLAMA_THREADS} \
|
|
--cont-batching
|
|
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
StartLimitBurst=3
|
|
StartLimitIntervalSec=60
|
|
|
|
# Resource limits
|
|
MemoryMax=12G
|
|
CPUQuota=90%
|
|
|
|
# Security hardening
|
|
NoNewPrivileges=true
|
|
ProtectSystem=strict
|
|
ProtectHome=read-only
|
|
ReadWritePaths=/opt/models
|
|
PrivateTmp=true
|
|
ProtectKernelTunables=true
|
|
ProtectControlGroups=true
|
|
RestrictSUIDSGID=true
|
|
|
|
# Logging
|
|
StandardOutput=journal
|
|
StandardError=journal
|
|
SyslogIdentifier=llama-server
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|