Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

The comparison really, seriously, doesn't make any sense.

It's like asking if anyone has benchmarked gnuCOBOL on OS/2 against LLVM ML IR.

You might be interested in llama.cpp's Vulkan backend_s_, that's more of an apples to apples comparison.



You can implement an idiomatic CNN in PyTorch or TF and compare their performance to this implementation. It's a perfectly reasonable comparison.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: