vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-09 22:05:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Initial commit

Browse source
This commit is contained in:
chenxl 2024-07-27 16:06:58 +08:00
commit 18c42e67df
247 changed files with 53775 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

32
ktransformers/ktransformers_ext/cuda/binding.cpp Normal file
View file

@ -0,0 +1,32 @@
/**
* @Description :
* @Author : Azure-Tang
* @Date : 2024-07-25 13:38:30
* @Version : 1.0.0
* @LastEditors : Azure
* @LastEditTime : 2024-07-26 08:36:03
* @Copyright (c) 2024 by KVCache.AI, All Rights Reserved.
**/
#include "custom_gguf/ops.h"
#include "gptq_marlin/ops.h"
// Python bindings
#include <pybind11/pybind11.h>
#include <pybind11/stl.h>
#include <torch/library.h>
#include <torch/extension.h>
#include <torch/torch.h>
// namespace py = pybind11;
PYBIND11_MODULE(KTransformersOps, m) {
m.def("dequantize_q8_0", &dequantize_q8_0, "Function to dequantize q8_0 data.",
py::arg("data"), py::arg("blk_size"), py::arg("device"));
m.def("dequantize_q6_k", &dequantize_q6_k, "Function to dequantize q6_k data.",
py::arg("data"), py::arg("blk_size"), py::arg("device"));
m.def("dequantize_q4_k", &dequantize_q4_k, "Function to dequantize q4_k data.",
py::arg("data"), py::arg("blk_size"), py::arg("device"));
m.def("gptq_marlin_gemm", &gptq_marlin_gemm, "Function to perform GEMM using Marlin quantization.",
py::arg("a"), py::arg("b_q_weight"), py::arg("b_scales"), py::arg("g_idx"),
py::arg("perm"), py::arg("workspace"), py::arg("num_bits"), py::arg("size_m"),
py::arg("size_n"), py::arg("size_k"), py::arg("is_k_full"));
}