Kernels:

phanerozoic
/

fp4-train

Kernel card Files Files and versions

fp4-train / torch-ext

6.05 kB

Ctrl+K

Ctrl+K

2 contributors

History: 2 commits

CharlesCNorton

fp4-train: add fp4_mm, the native Blackwell NVFP4 tensor-core matmul (10x over the dequant path)

3be46d1 24 days ago

fp4_train
fp4-train: add fp4_mm, the native Blackwell NVFP4 tensor-core matmul (10x over the dequant path) 24 days ago
torch_binding.cpp
545 Bytes
Add fp4-train source, tests, and model card 25 days ago
torch_binding.h
317 Bytes
Add fp4-train source, tests, and model card 25 days ago