2 commits

Author	SHA1	Message	Date
Till-JS	7c9c2645e3	🐛 fix(mana-stt): adjust vLLM config for CPU mode ... - Reduce max-model-len to 4096 for CPU compatibility - Add max-num-batched-tokens matching the context size - Add enforce-eager for stable CPU inference Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-11 16:14:14 +01:00
Till-JS	60394076e5	✨ feat(mana-stt): add vLLM integration for Voxtral transcription ... - Add vllm_service.py as proxy to vLLM server for Voxtral 3B/4B - Add voxtral_api_service.py for Mistral API fallback - Update main.py with /transcribe/voxtral endpoint using vLLM - Add /transcribe/auto endpoint with automatic fallback chain - Create setup-vllm.sh and start-vllm-voxtral.sh scripts - Add launchd plist files for Mac Mini deployment - Add install-services.sh for automated service installation Architecture: - vLLM server runs Voxtral models on port 8100 - mana-stt proxies to vLLM with Mistral API fallback - Fallback chain: vLLM -> Mistral API Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-11 16:10:00 +01:00