I see the app/relax_examples directory, but all the example are target to llvm.
CUDA is still not available?
I see the app/relax_examples directory, but all the example are target to llvm.
CUDA is still not available?
CUDA and other backends are supported. We build the mlc-llm project on top of Relax, which deploys LLM to GPUs, Mobile and Web
thank you! so the unity now has an application project, but lacks documents?
Seems the suggested docs is the mlc course?
直接看MLC-LLM吧,docs总是滞后的。