Download launch_server.sh from otherhalf-dev/whisper-large-v2-tensorrt-2401: direct link, hf CLI and curl.
- Browser
- Download file 425 Bytes
-
https://huggingface.co/otherhalf-dev/whisper-large-v2-tensorrt-2401/resolve/main/launch_server.sh
- Command line
-
hf download hf://otherhalf-dev/whisper-large-v2-tensorrt-2401/launch_server.sh
-
curl -L -o launch_server.sh https://huggingface.co/otherhalf-dev/whisper-large-v2-tensorrt-2401/resolve/main/launch_server.sh
425 Bytes
| # export CUDA_VISIBLE_DEVICES="0" | |
| model_repo_path=./model_repo_whisper_trtllm | |
| nohup tritonserver --model-repository $model_repo_path \ | |
| --pinned-memory-pool-byte-size=2048000000 \ | |
| --cuda-memory-pool-byte-size=0:4096000000 \ | |
| --http-port 7015 \ | |
| --metrics-port 5004 \ | |
| --grpc-port 7014 \ | |
| > tritonserver.out 2>&1 & | |