mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 34 Packages Projects Releases Wiki Activity

Remove support for Nvidia & AMD GPU, because the oneAPI plugin for Nvidia & AMD GPU is unavailable: download/installation channels are out of work. (#19246)

Browse Source 
User can't build up the software for Nvidia & AMD GPU.
rm the oneMath since it is only used in NV and AMD code path.
This commit is contained in:
Neo Zhang
2026-02-02 21:06:21 +08:00
committed by GitHub
parent 4d5e972673
commit bf38346d13
7 changed files with 60 additions and 274 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-sycl/wkv.cpp
+1 -1
View File
@@ -1,7 +1,7 @@
#include <sycl/sycl.hpp>
#include "wkv.hpp"
constexpr int WKV_BLOCK_SIZE = 64; // Matching CUDA_WKV_BLOCK_SIZE
constexpr int WKV_BLOCK_SIZE = 64;
// Helper function for the main kernel
template <int block_size>