-
-
Notifications
You must be signed in to change notification settings - Fork 11.1k
Truncation control for embedding models #14776
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
Truncation control for embedding models #14776
Conversation
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]>
|
👋 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 🚀 |
|
@DarkLight1337 , this is ready for review. Some CI step seems to be hanging, but all others have passed. |
Signed-off-by: Max de Bayser <[email protected]>
Head branch was pushed to by a user without write access
Signed-off-by: Max de Bayser <[email protected]>
Head branch was pushed to by a user without write access
|
@DarkLight1337 , all tests are passing now |
Signed-off-by: Gabriel Marinho <[email protected]> Signed-off-by: Max de Bayser <[email protected]> Co-authored-by: Max de Bayser <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]> Signed-off-by: Max de Bayser <[email protected]> Co-authored-by: Max de Bayser <[email protected]> Signed-off-by: Mu Huai <[email protected]>
Signed-off-by: Gabriel Marinho <[email protected]> Signed-off-by: Max de Bayser <[email protected]> Co-authored-by: Max de Bayser <[email protected]> Signed-off-by: Yuqi Zhang <[email protected]>
Issue #13489 (#13489)
Enables truncation control for offline and online API for embedding models via the paramenter
truncate_prompt_tokens. Whentruncate_prompt_tokens=-1the maximum prompt length that the model supports is used. When it exceeds the maximum prompt length, an error is raised. When 0 <truncate_prompt_tokens< maximum prompt length, the prompt is truncated.