You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
we are developing a library for high throughput LLM serving (https://github.com/vllm-project/vllm) and we are running into the 100MB limit. Could you increase it to 200MB for us? Unfortunately the wheel size needs to be a little larger than usual since the wheels include a bunch of GPU code and kernels which need to be compiled for different architectures.
Dear all,
we are developing a library for high throughput LLM serving (https://github.com/vllm-project/vllm) and we are running into the 100MB limit. Could you increase it to 200MB for us? Unfortunately the wheel size needs to be a little larger than usual since the wheels include a bunch of GPU code and kernels which need to be compiled for different architectures.
Thanks a lot for your help!
cc @WoosukKwon @zhuohan123 @simon-mo
The text was updated successfully, but these errors were encountered: