jdelony/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-27 23:50:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix PDL CC check for JIT compilation (#23471)

Browse Source
This commit is contained in:
Johannes Gäßler 2026-05-21 23:35:29 +02:00 committed by GitHub
parent bb28c1fe24
commit 4f0e43da6f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-cuda/common.cuh
View File

@ -1561,7 +1561,8 @@ static __inline__ void ggml_cuda_kernel_launch(Kernel kernel, const ggml_cuda_ke
return env == nullptr || std::atoi(env) != 0;
}();
if (env_pdl_enabled && ggml_cuda_info().devices[ggml_cuda_get_device()].cc >= GGML_CUDA_CC_HOPPER) {
const int cc = ggml_cuda_info().devices[ggml_cuda_get_device()].cc;
if (env_pdl_enabled && ggml_cuda_highest_compiled_arch(cc) >= GGML_CUDA_CC_HOPPER) {
auto pdl_cfg = ggml_cuda_pdl_config(launch_params);
CUDA_CHECK(cudaLaunchKernelEx(&pdl_cfg.cfg, kernel, std::forward<Args>(args)... ));