wehub-resource-sync
ec436095dd
Book-CI / test (macos-latest) (push) Has been cancelled
Book-CI / test (ubuntu-latest) (push) Has been cancelled
Book-CI / test (windows-latest) (push) Has been cancelled
Release Fake Tag / publish (push) Has been cancelled
Deploy / deploy (macos-latest) (push) Has been cancelled
Deploy / deploy (ubuntu-latest) (push) Has been cancelled
Deploy / deploy (windows-latest) (push) Has been cancelled
Release to PyPI / Build & publish sglang-kt (push) Has been cancelled
Release to PyPI / Build kt-kernel (Python 3.11) (push) Has been cancelled
Release to PyPI / Build kt-kernel (Python 3.12) (push) Has been cancelled
Release to PyPI / Publish kt-kernel to PyPI (push) Has been cancelled
30 lines
1.7 KiB
C
30 lines
1.7 KiB
C
/**
|
|
* @Description :
|
|
* @Author : Azure-Tang
|
|
* @Date : 2024-07-22 09:27:55
|
|
* @Version : 1.0.0
|
|
* @LastEditors : kkk1nak0
|
|
* @LastEditTime : 2024-08-12 03:48:46
|
|
* @Copyright (c) 2024 by KVCache.AI, All Rights Reserved.
|
|
**/
|
|
#pragma once
|
|
|
|
#include <torch/extension.h>
|
|
#include <torch/library.h>
|
|
#include <torch/torch.h>
|
|
|
|
torch::Tensor dequantize_q8_0(const int8_t* data, const int num_bytes, const int blk_size, const int ele_per_blk,
|
|
const torch::Device device, const torch::Dtype target_dtype);
|
|
torch::Tensor dequantize_q6_k(const int8_t* data, const int num_bytes, const int blk_size, const int ele_per_blk,
|
|
const torch::Device device, const torch::Dtype target_dtype);
|
|
torch::Tensor dequantize_q5_k(const int8_t* data, const int num_bytes, const int blk_size, const int ele_per_blk,
|
|
const torch::Device device, const torch::Dtype target_dtype);
|
|
torch::Tensor dequantize_q4_k(const int8_t* data, const int num_bytes, const int blk_size, const int ele_per_blk,
|
|
const torch::Device device, const torch::Dtype target_dtype);
|
|
torch::Tensor dequantize_q3_k(const int8_t* data, const int num_bytes, const int blk_size, const int ele_per_blk,
|
|
const torch::Device device, const torch::Dtype target_dtype);
|
|
torch::Tensor dequantize_q2_k(const int8_t* data, const int num_bytes, const int blk_size, const int ele_per_blk,
|
|
const torch::Device device, const torch::Dtype target_dtype);
|
|
torch::Tensor dequantize_iq4_xs(const int8_t* data, const int num_bytes, const int blk_size, const int ele_per_blk,
|
|
const torch::Device device, const torch::Dtype target_dtype);
|