feat: add proactive rate-limit guard for NIM 40 req/min a8c86bb verified raazkumar commited on 3 days ago
feat: add rpm_limit=40 hint for NVIDIA NIM local provider 2266b31 verified raazkumar commited on 4 days ago
feat: add local model provider support to llm_params.py 286afc5 verified raazkumar commited on 4 days ago