till/managarten
1
0
Fork 0
mirror of https://github.com/Memo-2023/mana-monorepo.git synced 2026-05-14 23:41:08 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
managarten/services/mana-stt/scripts
History
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
..
setup-vllm.sh ✨ feat(mana-stt): add vLLM integration for Voxtral transcription 2026-02-11 16:10:00 +01:00
start-vllm-voxtral.sh 🐛 fix(mana-stt): adjust vLLM config for CPU mode 2026-02-11 16:14:14 +01:00