|
const TFusedMHAKernelList * | getXMMAKernels (const typename TFusedMHAKernelList::KernelMeta *pKernelList, unsigned int nbKernels, Data_type type, unsigned int sm) |
|
|
std::unordered_map< uint64_t, const std::unique_ptr< TFusedMHAKernelList > > | mKernels |
|
◆ TFusedMHAKernelFactory()
template<typename TFusedMHAKernelList >
◆ getXMMAKernels()
template<typename TFusedMHAKernelList >
const TFusedMHAKernelList* bert::TFusedMHAKernelFactory< TFusedMHAKernelList >::getXMMAKernels |
( |
const typename TFusedMHAKernelList::KernelMeta * |
pKernelList, |
|
|
unsigned int |
nbKernels, |
|
|
Data_type |
type, |
|
|
unsigned int |
sm |
|
) |
| |
|
inline |
◆ Get()
template<typename TFusedMHAKernelList >
◆ hashID()
template<typename TFusedMHAKernelList >
◆ mKernels
template<typename TFusedMHAKernelList >
The documentation for this class was generated from the following file:
- fused_multihead_attention.h