R
RunPod•2mo ago
Gabriel Bianconi

"Error saving template. Please contact support or try again later." when using vLLM Quick Deploy

I managed to launch two endpoints successfully. The third endpoint displays the error above when I click "Deploy".
Solution:
Hey Gabriel! I believe to found the issue. We used the model name as a prefix for template name but it caused issues when the model name is too long (for example llama-3-8b-instruct) A fix will be rolling out in the next few days. Sorry for the inconvenience!...
Jump to solution
3 Replies
Gabriel Bianconi
Gabriel Bianconi•2mo ago
Thsi breaks when the HF repository name is too long... pls fix!
PatrickR
PatrickR•2mo ago
What's the HF model name?
Solution
Jacob
Jacob•2mo ago
Hey Gabriel! I believe to found the issue. We used the model name as a prefix for template name but it caused issues when the model name is too long (for example llama-3-8b-instruct) A fix will be rolling out in the next few days. Sorry for the inconvenience!
Want results from more Discord servers?
Add your server
More Posts
jupyter notebookWill connecting to the port of GPU instance show the same progress and jupyter notebook I am runningSuper slow network speeds on some pods.Some pods have really really slow network speeds and take an absolute age to install requirements inWhy is it considered that it is always in the queue state in serveless and cannot be executed?The task has been stuck in the queue. The serverless Endpoint id is 9ufpu7wjug1mqc and the task id iPower cappedIt appens a lot on french GPU's idk why buy the power is hard capped very lowServerless vLLM doesn't work and gives no error messageI've spent a few hours trying to deploy a serverless vLLM endpoint according to the instructions at connect to pod 1 from pod 2both pods have the same ip, but can't communicate to each other. Why?Hey all, why does this worker keep alive after the task is completed?Here is the request ID: d7aa74ec-5b1f-4af9-8bf4-d8211740019b-u1 According to log, there is no crashHow to change from root user?Sorry for dumb question! I'm trying to start a project by installing packages within my venv but getFailed to return job resultsMy serverless endpoint is timing out after the client configured timeout of 30 seconds, even though http service [port 7860] Not ReadyI broke runpod. NEW to LLM. Use runpod webui/terminal and huggingface. I receive this error regar