Any plans for merging into mainline vLLM?
#16
by pathosethoslogos - opened
Just wondering if there are any plans for it, as they automatically build Docker images for various hardware specs/CUDA versions/etc.
Relatively sure the code was already merged to the vllm main. https://github.com/vllm-project/vllm/pull/51045
Relatively sure the code was already merged to the vllm main. https://github.com/vllm-project/vllm/pull/51045
Oh I see, great!
The model card still says 'Install our vLLM' with your specific vLLM link. Probably need to be updated then, right?
Either way, great! I will have to give this a go. :)