Fix device placement for tokenizer outputs before model inference 64c014e jeanbaptdzd commited on 20 days ago
Refactor: Address code shortcomings and align with HF best practices dc14519 jeanbaptdzd commited on 20 days ago
Rename vllm.py to transformers_provider.py - clarify implementation and force rebuild afd6869 jeanbaptdzd commited on Nov 2
Initial commit: FastAPI service with OpenAI-compatible API and PRIIPs extraction f6fdf6a jeanbaptdzd commited on Oct 28