|
|
|
|
|
by andy99
916 days ago
|
|
The original mamba code has a lot of speed optimizations and other stuff that make it difficult to immediately get so this will help with learning. I can't help but also plug my own Mamba inference implementation. https://github.com/rbitr/llm.f90/tree/master/ssm For inference one token at a time everything simplifies considerably. |
|
I know it underpins a lot of time-tested scientific code, often wrapped by libraries like PyTorch and Numpy, but Fortran isn't exactly a popular language nowadays. What's your rationale for using it?