R
RunPod3w ago
Yebs

Can you now run gemma 3 in the vllm container?

In the serverless, its seems im getting an error, any help on this
18 Replies
Jason
Jason3w ago
can you send the error
Yebs
YebsOP3w ago
I deleted it but it seems bc gemma3 is a new model so transformer is relatively outdated afaik?
Jason
Jason3w ago
hmm did you use vllm? or only transformer? yeah maybe its a good thing to check first for compatibility
Yebs
YebsOP3w ago
I used the preset vllm, llama 3.2b worked but the new gemma 3 didnt
Dj
Dj3w ago
vLLM needs to publish an update first unfortunately You can use vLLM directly from the main branch, but that's not super easy if you're using our vLLM template iirc
Jason
Jason3w ago
I think we can update and build our own vllm template from that vllm-worker repo in github easily Just update the requirement.txt or wherever installs the vllm
Bj9000
Bj90002w ago
Looks like vllm v0.8.0 added gemma3 support will the serverless vllm be updated soon?
Jason
Jason2w ago
usually its delayed, so probably a few days/ weeks late
Aizen
Aizen5d ago
Hi, i have the same issue , have you resolved it? , if then please help me out with it too
Yebs
YebsOP5d ago
I used ollana Ollama
Aizen
Aizen5d ago
Okay
Jason
Jason5d ago
yes i think vllm is updated already
Javier
Javier4d ago
I deployed an end point to try to call gemma3:4b but nothing is happening when I call it, anybody managed?
Jason
Jason3d ago
Yes it works
Jason
Jason3d ago
just now i've tried for you!
Jason
Jason3d ago
you need access from hf + hf token to access it
Jason
Jason3d ago
use vllm to configure + check the allow remote code options in the config ( in runpod menu when configuring vllm )
No description
Jason
Jason3d ago
second image is the next page
No description
No description

Did you find this page helpful?