{ | |
"id": "deploy-whisper-vllm-gpu", | |
"description": "Build and deploy vLLM based Whisper on Inference Endpoint", | |
"instance_type": "nvidia-l4", | |
"instance_size": "x1", | |
"model": "openai/whisper-large-v3-turbo" | |
} |
{ | |
"id": "deploy-whisper-vllm-gpu", | |
"description": "Build and deploy vLLM based Whisper on Inference Endpoint", | |
"instance_type": "nvidia-l4", | |
"instance_size": "x1", | |
"model": "openai/whisper-large-v3-turbo" | |
} |