LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

cuda: fix warnings for unused variable/function (#26688)

Browse Source
This commit is contained in:
David Friehs
2026-08-07 07:51:56 +03:00
committed by GitHub
parent d8d9887228
commit 5b87ed30f8
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/ggml-cuda.cu
+1
View File
@@ -5209,6 +5209,7 @@ static bool ggml_backend_cuda_device_offload_op(ggml_backend_dev_t dev, const gg
static ggml_backend_event_t ggml_backend_cuda_device_event_new(ggml_backend_dev_t dev) {
#ifdef GGML_CUDA_NO_PEER_COPY
GGML_UNUSED(dev);
return nullptr;
#else
ggml_backend_cuda_device_context * dev_ctx = (ggml_backend_cuda_device_context *)dev->context;
ggml/src/ggml-cuda/quantize.cu
+1 -1
View File
@@ -8,7 +8,6 @@ struct __builtin_align__(32) float8 {
float x; float y; float z; float w;
float p; float q; float r; float s;
};
#endif
#if CUDART_VERSION >= 12080
static __device__ __forceinline__ float nvfp4_native_scale_error(
@@ -49,6 +48,7 @@ static __device__ __forceinline__ float nvfp4_native_scale_error(
return err;
}
#endif // CUDART_VERSION >= 12080
#endif // defined(BLACKWELL_MMA_AVAILABLE)
__launch_bounds__(CUDA_QUANTIZE_BLOCK_SIZE, 1)
static __global__ void quantize_q8_1(