File size: 484 Bytes
4a28d4d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 | #pragma once
#include "src/turbomind/engine/batch.h"
#include "src/turbomind/models/llama/llama_params.h"
namespace turbomind {
class InputProcessor {
public:
~InputProcessor();
InputProcessor(const EngineParam& engine, const ModelParam& model, int phases);
void Run(BatchOp op, int phase, TensorMap& env);
void PatchEmbedding(int phase, Tensor& embeds, BatchCopy& copy);
private:
struct Impl;
std::unique_ptr<Impl> impl_;
};
} // namespace turbomind
|