cuda_sparse_nvfp4_naive_n2048_k2048
FlashInfer-Bench baselines · cuda · Apache-2.0
Kernel source · 10 lines ↓holds 2 records
Use it
Vendorable · source mirrored · Apache-2.0View source →
No package. Vendor the mirrored source: 10 lines, Apache-2.0, pinned at da91508.
main.cpp
curl "https://kernelindex.com/api/v1/implementations/flashinfer-cuda-sparse-nvfp4-naive-n2048-k2048?include=source"interfacecuda
revisionda915083d4c7
symbolrun
pathmain.cpp
Compatibility
measured onNVIDIA B200
declared hardwareNVIDIA B200
architecturessm_100
dtypesint8
Benchmark evidence
2 measurements across 1 GPU, fastest first.
Operation / workload
Hardware
Latency
Rank
Observed
Reproduction-ready · How evidence levels are derived →
Source and license
sourcehttps://huggingface.co/datasets/flashinfer-ai/flashinfer-trace
commitda915083d4c7c5e61aa3005e3d17ae488e0fc71c
revision digestsha256:997045efe13d7270fd9bad2fd114794bbb5f6c5e272bd6ca75a5b49c94a5f1b4
license declaredApache-2.0
license concludedApache-2.0
authorsbaseline
imported2026-08-16
Techniques
Extracted from the mirrored source by pattern, never inferred. Each row cites its line.
fp4
PYBIND11_MODULE(TORCH_EXTENSION_NAME,m){m.def("run",&run,"sparse nvfp4 gemm",py::arg("A_vals"),py::arg("A_meta"),py::arg("A_scale"),py::arg("B_fp4"),py::arg("B_scale"));}Kernel source
main.cpp10 lines
#include "kernel.h"
#include <torch/extension.h>
torch::Tensor run(torch::Tensor A_vals,torch::Tensor A_meta,torch::Tensor A_scale,torch::Tensor B_fp4,torch::Tensor B_scale){
auto Av=A_vals.contiguous();auto Am=A_meta.contiguous();auto As=A_scale.contiguous();auto B=B_fp4.contiguous();auto Bs=B_scale.contiguous();
const auto M=Av.size(0); const auto N=B.size(0);
auto C=torch::empty({M,N},torch::dtype(at::kBFloat16).device(Av.device()));
launch_sparse_nvfp4(Av,Am,As,B,Bs,C); return C;
}
PYBIND11_MODULE(TORCH_EXTENSION_NAME,m){m.def("run",&run,"sparse nvfp4 gemm",py::arg("A_vals"),py::arg("A_meta"),py::arg("A_scale"),py::arg("B_fp4"),py::arg("B_scale"));}
Source code from FlashInfer-Bench (flashinfer-ai/flashinfer-trace) · Apache-2.0
Best evidence level for this revision: reproducible
JSON