Skip to content
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

Enable inference mode for deepspeed tp serving #11742

Merged
merged 1 commit into from
Aug 8, 2024
Merged

Enable inference mode for deepspeed tp serving #11742

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
4 changes: 3 additions & 1 deletion python/llm/example/GPU/Deepspeed-AutoTP-FastAPI/serving.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,11 +116,13 @@ def load_model(model_path, low_bit):
# Use IPEX-LLM `optimize_model` to convert the model into optimized low bit format
# Convert the rest of the model into float16 to reduce allreduce traffic
model = optimize_model(model.module.to(f"cpu"), low_bit=low_bit).to(torch.float16)

# Next, use XPU as accelerator to speed up inference
current_accel = XPU_Accelerator()
set_accelerator(current_accel)

model=model.eval()

# Move model back to xpu
model = model.to(f"xpu:{local_rank}")
model = BenchmarkWrapper(model)
Expand Down
Loading