public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

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

This commit is contained in:
David Friehs 2026-08-07 06:51:56 +02:00 committed by Georgi Gerganov
parent 5693378610
commit 79ab70c922
2 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/src/ggml-cuda/ggml-cuda.cu
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) { static ggml_backend_event_t ggml_backend_cuda_device_event_new(ggml_backend_dev_t dev) {
#ifdef GGML_CUDA_NO_PEER_COPY #ifdef GGML_CUDA_NO_PEER_COPY
GGML_UNUSED(dev);
return nullptr; return nullptr;
#else #else
ggml_backend_cuda_device_context * dev_ctx = (ggml_backend_cuda_device_context *)dev->context; ggml_backend_cuda_device_context * dev_ctx = (ggml_backend_cuda_device_context *)dev->context;

2
ggml/src/ggml-cuda/quantize.cu
View File

@ -8,7 +8,6 @@ struct __builtin_align__(32) float8 {
float x; float y; float z; float w; float x; float y; float z; float w;
float p; float q; float r; float s; float p; float q; float r; float s;
}; };
#endif
#if CUDART_VERSION >= 12080 #if CUDART_VERSION >= 12080
static __device__ __forceinline__ float nvfp4_native_scale_error( static __device__ __forceinline__ float nvfp4_native_scale_error(
@ -49,6 +48,7 @@ static __device__ __forceinline__ float nvfp4_native_scale_error(
return err; return err;
} }
#endif // CUDART_VERSION >= 12080 #endif // CUDART_VERSION >= 12080
#endif // defined(BLACKWELL_MMA_AVAILABLE)
__launch_bounds__(CUDA_QUANTIZE_BLOCK_SIZE, 1) __launch_bounds__(CUDA_QUANTIZE_BLOCK_SIZE, 1)
static __global__ void quantize_q8_1( static __global__ void quantize_q8_1(