whisper-vllm-gpu / .hfjobs /deploy.json
Morgan Funtowicz
test(hfjobs): add instance type and size to deploy.json
922eee4
raw
history blame contribute delete
226 Bytes
{
"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"
}