Open dsingal0 opened 4 days ago
vllm's next release will add support for gemma2 9/27B. Until then you'd have to build from source on top of a pytorch image which takes 30+ minutes to deploy. https://github.com/vllm-project/vllm/issues/5806
vllm's next release will add support for gemma2 9/27B. Until then you'd have to build from source on top of a pytorch image which takes 30+ minutes to deploy. https://github.com/vllm-project/vllm/issues/5806