Remove some dead code. #10372
Annotations
10 errors and 6 warnings
|
Build and Clean Binaries:
onnxruntime/core/providers/cuda/llm/attention.cc#L219
'=': cannot convert from 'const onnxruntime::cuda::Attention<float>::ComputeInternal::CudaT *' to 'const U *'
|
|
Build and Clean Binaries:
onnxruntime/core/providers/cuda/llm/attention.cc#L218
'=': cannot convert from 'const onnxruntime::cuda::Attention<float>::ComputeInternal::CudaT *' to 'const U *'
|
|
Build and Clean Binaries:
onnxruntime/core/providers/cuda/llm/attention.cc#L217
'=': cannot convert from 'const onnxruntime::cuda::Attention<float>::ComputeInternal::CudaT *' to 'const T *'
|
|
Build and Clean Binaries:
onnxruntime/core/providers/cuda/llm/attention.cc#L216
'=': cannot convert from 'const onnxruntime::cuda::Attention<float>::ComputeInternal::CudaT *' to 'const T *'
|
|
Build and Clean Binaries:
onnxruntime/core/providers/cuda/llm/attention.cc#L215
'=': cannot convert from 'const onnxruntime::cuda::Attention<float>::ComputeInternal::CudaT *' to 'const T *'
|
|
Build and Clean Binaries:
onnxruntime/core/providers/cuda/llm/attention.cc#L199
'onnxruntime::contrib::cuda::GroupQueryAttentionData<T,U> onnxruntime::contrib::cuda::GroupQueryAttentionData(onnxruntime::contrib::cuda::GroupQueryAttentionData<T,U>)': expects 1 arguments - 0 provided
|
|
Build and Clean Binaries:
onnxruntime/core/providers/cuda/llm/attention.cc#L199
'onnxruntime::contrib::cuda::GroupQueryAttentionData<T,U> onnxruntime::contrib::cuda::GroupQueryAttentionData(void)': could not deduce template argument for 'U'
|
|
Build and Clean Binaries:
onnxruntime/core/providers/cuda/llm/attention.cc#L199
'onnxruntime::contrib::cuda::GroupQueryAttentionData<T,U> onnxruntime::contrib::cuda::GroupQueryAttentionData(void)': could not deduce template argument for 'T'
|
|
Build and Clean Binaries:
onnxruntime/core/providers/cuda/llm/attention.cc#L199
cannot deduce template arguments for 'onnxruntime::contrib::cuda::GroupQueryAttentionData'
|
|
Build and Clean Binaries:
onnxruntime/core/providers/cuda/llm/attention.cc#L199
'onnxruntime::contrib::cuda::GroupQueryAttentionData': too few template arguments
|
|
Build and Clean Binaries:
onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1234
epilog offset from end of function exceeds 4095
|
|
Build and Clean Binaries:
onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1227
epilog offset from end of function exceeds 4095
|
|
Build and Clean Binaries:
onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1220
epilog offset from end of function exceeds 4095
|
|
Build and Clean Binaries:
onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1213
epilog offset from end of function exceeds 4095
|
|
Build and Clean Binaries:
onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1206
epilog offset from end of function exceeds 4095
|
|
Build and Clean Binaries:
onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1199
epilog offset from end of function exceeds 4095
|
Loading