Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ggml : check return value of CUB calls used in argsort and top-k (they all return cudaError_t) (#21676)

Browse Source 
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
This commit is contained in:
fairydreaming
2026-04-09 21:17:11 +08:00
committed by GitHub
co-authored by Stanisław Szymczyk
parent c8ac02fa1b
commit 009a113326
2 changed files with 20 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/top-k.cu
+4 -4
View File
@@ -25,14 +25,14 @@ static void top_k_cub(ggml_cuda_pool & pool,
auto indexes_in = cuda::make_counting_iterator(0);
size_t temp_storage_bytes = 0;
DeviceTopK::MaxPairs(nullptr, temp_storage_bytes, src, cuda::discard_iterator(), indexes_in, dst, ncols, k,
env);
CUDA_CHECK(DeviceTopK::MaxPairs(nullptr, temp_storage_bytes, src, cuda::discard_iterator(), indexes_in, dst, ncols, k,
env));
ggml_cuda_pool_alloc<uint8_t> temp_storage_alloc(pool, temp_storage_bytes);
void * d_temp_storage = temp_storage_alloc.get();
DeviceTopK::MaxPairs(d_temp_storage, temp_storage_bytes, src, cuda::discard_iterator(), indexes_in, dst,
ncols, k, env);
CUDA_CHECK(DeviceTopK::MaxPairs(d_temp_storage, temp_storage_bytes, src, cuda::discard_iterator(), indexes_in, dst,
ncols, k, env));
}
#elif defined(GGML_CUDA_USE_CUB) // CUB_TOP_K_AVAILABLE