e3e79e9e8a
Co-authored-by: Robert Irvine <robert@seamlessml.com> Co-authored-by: root <rirv938@gmail.com> Co-authored-by: Casper <casperbh.96@gmail.com> Co-authored-by: julian-q <julianhquevedo@gmail.com>
16 lines
303 B
C++
16 lines
303 B
C++
#include <torch/extension.h>
|
|
|
|
torch::Tensor awq_gemm(
|
|
torch::Tensor _in_feats,
|
|
torch::Tensor _kernel,
|
|
torch::Tensor _scaling_factors,
|
|
torch::Tensor _zeros,
|
|
int split_k_iters);
|
|
|
|
PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
|
|
m.def(
|
|
"awq_gemm",
|
|
&awq_gemm,
|
|
"Quantized GEMM for AWQ");
|
|
}
|