😀
I may be slow to respond.
- Los Angeles
Starred repositories
3
stars
written in Cuda
Clear filter
Instant neural graphics primitives: lightning fast NeRF and more
A massively parallel, optimal functional runtime in Rust
CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge techniques in sparse architecture, speculative sampling and qua…