DeepSeek/DeepEP
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepEP synced 2025-06-26 18:28:11 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add automatic warp count control for low-latency dispatch

Browse Source
This commit is contained in:
Chenggang Zhao
2025-06-16 11:31:38 +08:00
parent 4e923188f7
commit 632c81f1d7
6 changed files with 59 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
csrc/config.hpp
View File

@@ -6,13 +6,13 @@
namespace deep_ep {
template <typename dtype_t>
dtype_t cell_div(dtype_t a, dtype_t b) {
dtype_t ceil_div(dtype_t a, dtype_t b) {
return (a + b - 1) / b;
}
template <typename dtype_t>
dtype_t align(dtype_t a, dtype_t b) {
return cell_div<dtype_t>(a, b) * b;
return ceil_div<dtype_t>(a, b) * b;
}
struct Config {