Mila
Deep Neural Network Library
Loading...
Searching...
No Matches
Dnn.Components.LlamaTransformer Module Reference

Exported Modules

module  Compute.DeviceTypeTraits
module  Dnn.ActivationType
module  Dnn.Components.RmsNorm
module  Dnn.ITensor
module  Compute.ExecutionContext
module  Compute.DeviceType
module  Serialization.ModelArchive
module  Dnn.Quantization.Weight.Policies
module  Compute.GqaState
module  Dnn.TensorDataTypeTraits
module  Dnn.TensorTypes
module  Dnn.RuntimeMode
module  Compute.CpuMemoryResource
module  Dnn.ModelType
module  Dnn.Components.Linear
module  Dnn.Tensor
module  Compute.DeviceId
module  Compute.ExecutionContextFactory
module  Dnn.LanguageModelNetwork
module  Dnn.Components.Rope
module  Serialization.Tensor
module  Serialization.WeightsReader
module  Dnn.ComponentType
module  Dnn.TensorDataType
module  Logging.Logger
module  Dnn.Quantization.KvCache.Policy
module  Compute.DeviceAllocation
module  Compute.Device
module  Dnn.Components.TokenEmbedding
module  Dnn.Component
module  Compute.GqaWorkspace

Classes

class  Mila::Dnn::LlamaBlock< TDeviceType, TPrecision, TWeightQuant, TKvPolicy >
class  Mila::Dnn::LlamaConfig
 Network-level configuration for LLaMA-style transformer networks. More...
class  Mila::Dnn::LlamaTransformer< TDeviceType, TPrecision, TWeightQuantization, TKvCachePolicy >
 LLaMA-style transformer (decoder-only) for autoregressive token prediction. More...

Functions

LlamaConfig Mila::Dnn::Llama3_2_1B ()
 Usage Examples:
LlamaConfig Mila::Dnn::Llama3_2_3B ()
 Llama 3.2 3B.
LlamaConfig Mila::Dnn::Llama3_1_8B ()
 Llama 3.1 8B.
LlamaConfig Mila::Dnn::Llama3_1_70B ()
 Llama 3.1 70B.
LlamaConfig Mila::Dnn::Llama3_1_405B ()
 Llama 3.1 405B.
LlamaConfig Mila::Dnn::Llama3_8B ()
 Llama 3 8B (Original release).
LlamaConfig Mila::Dnn::Llama3_70B ()
 Llama 3 70B (Original release).
LlamaConfig Mila::Dnn::Llama2_7B ()
 Llama 2 7B.
LlamaConfig Mila::Dnn::Llama2_13B ()
 Llama 2 13B.
LlamaConfig Mila::Dnn::Llama2_70B ()
 Llama 2 70B.

Variables

constexpr int64_t Mila::Dnn::kLlamaPrefillChunkFloor = 128
constexpr int64_t Mila::Dnn::kLlamaPrefillChunkRungs [] = { 512, 256, 128 }

Files

file  Mila/Src/Dnn/Components/Transformers/LlaMa/Llama.ixx
 LLaMA-style decoder-only transformer network.
file  Mila/Src/Dnn/Components/Transformers/LlaMa/Llama.Block.ixx
 LLaMA transformer block – module partition of LlamaTransformer.
file  Mila/Src/Dnn/Components/Transformers/LlaMa/Llama.Config.ixx
 LLaMA network-level configuration.
file  Mila/Src/Dnn/Components/Transformers/LlaMa/Llama.Presets.ixx