apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-27 02:20:31 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Adapt for iluvatar gpu (#2684)

Browse Source
This commit is contained in:
liddk1121
2025-07-07 16:53:14 +08:00
committed by GitHub
parent 2579e8fea8
commit 1b54a2831e
50 changed files with 4485 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
custom_ops/gpu_ops/noauxtc_kernel.h
View File

@@ -17,11 +17,11 @@
#pragma once
#include <cooperative_groups.h>
#include <cooperative_groups/reduce.h>
#include "helper.h"
namespace cg = cooperative_groups;
constexpr unsigned FULL_WARP_MASK = 0xffffffff;
constexpr int32_t WARP_SIZE = 32;
constexpr int32_t BLOCK_SIZE = 512;
constexpr int32_t NUM_WARPS_PER_BLOCK = BLOCK_SIZE / WARP_SIZE;