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

reproduce oom #339

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

reproduce oom #339

Show file tree
Hide file tree
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
10 changes: 5 additions & 5 deletions vllm/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
model_name: "Llama 3.1 70B Instruct VLLM"
model_name: "Llama 3.1 8B Instruct VLLM oom"
python_version: py311
model_metadata:
example_model_input: {"prompt": "what is the meaning of life"}
repo_id: meta-llama/Meta-Llama-3.1-70B-Instruct
openai_compatible: true
repo_id: meta-llama/Meta-Llama-3.1-8B-Instruct
openai_compatible: false
vllm_config:
tensor_parallel_size: 4
tensor_parallel_size: 1
max_model_len: 4096
enable_prefix_caching: true
requirements:
- vllm==0.5.4
resources:
accelerator: A100:4
accelerator: A100
use_gpu: true
runtime:
predict_concurrency: 128
Expand Down
2 changes: 2 additions & 0 deletions vllm/model/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,6 +122,8 @@ def load(self):
logger.info(result.stdout)
except subprocess.CalledProcessError as e:
logger.error(f"Command failed with code {e.returncode}: {e.stderr}")
# testing
raise RuntimeError("Oops!")

async def predict(self, model_input):
if "messages" not in model_input and "prompt" not in model_input:
Expand Down
Loading