This is stars and forks stats for /harrisonvanderbyl/rwkv-cpp-cuda repository. As of 29 Apr, 2024 this repository has 283 stars and 15 forks.
RWKV Cuda This is a super simple c++/cuda implementation of rwkv with no pytorch/libtorch dependencies. included is a simple example of how to use in both c++ and python. Features Direct Disk -> Gpu loading ( practically no ram needed ) Uint8 by default Incredibly fast No dependencies Simple to use Simple to build Optional Python binding using pytorch tensors as wrappers Native tokenizer! Windows Support! HIP(AMD) GPU support! Vulkan(All) Support! Distributable programs! (check actions for the...
RWKV Cuda This is a super simple c++/cuda implementation of rwkv with no pytorch/libtorch dependencies. included is a simple example of how to use in both c++ and python. Features Direct Disk -> Gpu loading ( practically no ram needed ) Uint8 by default Incredibly fast No dependencies Simple to use Simple to build Optional Python binding using pytorch tensors as wrappers Native tokenizer! Windows Support! HIP(AMD) GPU support! Vulkan(All) Support! Distributable programs! (check actions for the...
repo | techs | stars | weekly | forks | weekly |
---|---|---|---|---|---|
code-sujan/mmc_workshop_ci | CSSPHPOther | 2 | 0 | 14 | 0 |
krmeet/sound-space-plus | GDScriptGLSLOther | 18 | +1 | 8 | 0 |
uber/cadence | GoOther | 7.3k | 0 | 744 | 0 |
ni/grpc-labview | LabVIEWC++Python | 67 | 0 | 52 | 0 |
tensorflow/flutter-tflite | DartCRuby | 296 | 0 | 53 | 0 |
ROCm-Developer-Tools/aomp | FortranCShell | 152 | 0 | 36 | 0 |
AnalogJ/scrutiny | GoHTMLOther | 3.5k | 0 | 121 | 0 |
anirudhmalik/xhunter | JavaJavaScriptOther | 447 | 0 | 116 | 0 |
logicalclocks/hopsworks-tutorials | Jupyter NotebookOther | 121 | 0 | 50 | 0 |
heclak/community-a4e-c | LuaC++C | 493 | 0 | 74 | 0 |