Skip to content

Fix hardcoded CUDA device in api.py to support MPS and CPU fallback #1516

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Mr-Neutr0n wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix hardcoded CUDA device in api.py to support MPS and CPU fallback #1516

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,16 +3,18 @@
import uvicorn, json, datetime
import torch

DEVICE = "cuda"
DEVICE_ID = "0"
CUDA_DEVICE = f"{DEVICE}:{DEVICE_ID}" if DEVICE_ID else DEVICE
DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
DEVICE_ID = "0" if DEVICE == "cuda" else None
CUDA_DEVICE = f"{DEVICE}:{DEVICE_ID}" if DEVICE == "cuda" and DEVICE_ID else DEVICE


def torch_gc():
if torch.cuda.is_available():
if DEVICE == "cuda" and torch.cuda.is_available():
with torch.cuda.device(CUDA_DEVICE):
torch.cuda.empty_cache()
torch.cuda.ipc_collect()
elif DEVICE == "mps":
torch.mps.empty_cache()


app = FastAPI()
Expand Down Expand Up @@ -51,6 +53,6 @@ async def create_item(request: Request):

if __name__ == '__main__':
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().to(DEVICE)
model.eval()
uvicorn.run(app, host='0.0.0.0', port=8000, workers=1)