xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-11 04:22:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

use abosolute path

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
yewentao256 2025-08-27 21:44:27 +00:00
parent e92676ef4e
commit afe23a2990
3 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
csrc/quantization/w8a8/fp8/per_token_group_quant.cu
View File

@ -1,6 +1,6 @@
#include <ATen/cuda/CUDAContext.h>
#include "../per_token_group_quant_8bit.h"
#include "quantization/w8a8/per_token_group_quant_8bit.h"
#include <cmath>
@ -8,9 +8,9 @@
#include <torch/all.h>
#include "../../vectorization.cuh"
#include "../../vectorization_utils.cuh"
#include "../../../dispatch_utils.h"
#include "quantization/vectorization.cuh"
#include "quantization/vectorization_utils.cuh"
#include "dispatch_utils.h"
__device__ __forceinline__ float GroupReduceMax(float val, const int tid) {
unsigned mask = 0xffff;

2
csrc/quantization/w8a8/int8/per_token_group_quant.cu
View File

@ -1,7 +1,7 @@
#include <ATen/cuda/CUDAContext.h>
#include <torch/all.h>
#include "../per_token_group_quant_8bit.h"
#include "quantization/w8a8/per_token_group_quant_8bit.h"
void per_token_group_quant_int8(const torch::Tensor& input,
torch::Tensor& output_q,

4
csrc/quantization/w8a8/int8/scaled_quant.cu
View File

@ -3,8 +3,8 @@
#include <cmath>
#include "../../../dispatch_utils.h"
#include "../../vectorization_utils.cuh"
#include "dispatch_utils.h"
#include "quantization/vectorization_utils.cuh"
#ifndef USE_ROCM
#include <cub/cub.cuh>