thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

CUDA : fix typo in clang pragma comment [no ci] (#18830)

Browse source
This commit is contained in:
Daniel Bevenius 2026-01-14 10:31:49 +01:00 • committed by GitHub
parent 635ef78ec5
commit 01cbdfd7eb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-cuda/fattn-vec.cuh
View file

@ -10,7 +10,7 @@ static constexpr __device__ int ggml_cuda_fattn_vec_get_nthreads_device() {
return 128; return 128;
} }
// Currenlty llvm with the amdgcn target dose not support unrolling loops // Currenlty llvm with the amdgcn target does not support unrolling loops
// that contain a break that can not be resolved at compile time. // that contain a break that can not be resolved at compile time.
#ifdef __clang__ #ifdef __clang__
#pragma clang diagnostic push #pragma clang diagnostic push