Sebastian Krüger cc0f55df38 fix: reduce max_model_len to 20000 to fit in 24GB VRAM

2025-11-23 15:43:37 +01:00

..

requirements.txt

fix: relax dependency version constraints for vllm compatibility

2025-11-23 13:33:46 +01:00

server.py

fix: reduce max_model_len to 20000 to fit in 24GB VRAM

2025-11-23 15:43:37 +01:00