|
Mila
Deep Neural Network Library
|
Exported Modules | |
| module | Compute.DeviceTypeTraits |
| module | Dnn.TensorTypes |
| module | Dnn.ComponentType |
| module | Compute.DeviceId |
| module | Dnn.Tensor |
| module | Compute.Device |
| module | Dnn.Components.GqaConfig |
| module | Dnn.Quantization.KvCache.Policy |
| module | Compute.ExecutionContext |
| module | Compute.DeviceType |
| module | Dnn.ITensor |
| module | Serialization.Mode |
| module | Compute.IKvCacheLifecycle |
| module | Compute.MemoryResource |
| module | Compute.GqaState |
| module | Dnn.TensorDataType |
| module | Compute.OperationTraits |
| module | Compute.IKvInference |
| module | Compute.CpuMemoryResource |
| module | Dnn.Component |
| module | Dnn.TensorDataTypeTraits |
| module | Serialization.ModelArchive |
| module | Compute.ExecutionContextFactory |
Classes | |
| class | Mila::Dnn::GroupedQueryAttention< TDeviceType, TComputePrecision, TKvPolicy > |
| Grouped-Query Attention module that accepts concatenated QKV input. More... | |
Files | |
| file | Mila/Src/Dnn/Components/Attention/GQA/GroupedQueryAttention.ixx |
| Grouped-Query Attention module (concatenated QKV input). | |