[Feature] add support for llama 3.2

[Stealthwriter]

Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
• 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
• 5. Please use English, otherwise it will be closed.

Describe the bug

data did not match any variant of untagged enum ModelWrapper at line 1251003 column 3

Reproduction

try to run llama 3.2 3b

Environment

docker

[shubhanshu786]

vLLM as already added support for Llama 3.2. SGLang, should do that too fast.

[zhyncs]

Yes, vLLM currently only supports a single image. @hnyls2002 is working on support Llama 3.2 3b functionality.

[81549361]

Yes, vLLM currently only supports a single image. @hnyls2002 is working on support Llama 3.2 3b functionality.

I just need to reinstall sglang and update some packages to reason about llama 3b

[merrymercy]

Will be ready soon #1551

[slin1237]

any ETA? And would this support all family and multiple images?

[merrymercy]

Yes, it will support all family and multi image.

[merrymercy]

supported by #1551