-
-
Notifications
You must be signed in to change notification settings - Fork 7.8k
[Benchmark] Add hf_stream arg to enable or disable datasets streaming loading #18989
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.
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
base: main
Are you sure you want to change the base?
Conversation
👋 Hi! Thank you for contributing to the vLLM project. 💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels. Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can either: Add 🚀 |
@JenZhao would mind have a review |
benchmarks/benchmark_throughput.py
Outdated
action="store_true", | ||
default=True, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I don't think this would work as intended; as we set action="store_true"
, args.hf_stream
is always True
regardless of user passing --hf-stream
option or not.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thx for remind, should not set a default value
Signed-off-by: wangli <[email protected]>
Signed-off-by: wangli <[email protected]>
Signed-off-by: wangli <[email protected]>
Signed-off-by: wangli <[email protected]>
Signed-off-by: wangli <[email protected]>
Signed-off-by: wangli <[email protected]>
This pr adds
hf_stream
arg for benchmark_serving to enable or disable datasets streaming loading, Because some users have to load the dataset from local due to network reasons, we added this parameter to let users decide whether to enable streaming loading