github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-06 11:00:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

expose n_gpu_layers parameter of llama.cpp (#1890)

Browse Source 
Also dynamically limit the GPU layers and context length fields to the maximum supported by the model.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
Jared Van Bortel
2024-01-31 14:17:44 -05:00
committed by GitHub
parent f549d5a70a
commit 061d1969f8
31 changed files with 381 additions and 157 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
gpt4all-backend/llamamodel_impl.h
View File

@@ -4,8 +4,9 @@
#ifndef LLAMAMODEL_H
#define LLAMAMODEL_H
#include <string>
#include <functional>
#include <memory>
#include <string>
#include <vector>
#include "llmodel.h"
@@ -17,23 +18,22 @@ public:
bool supportsEmbedding() const override { return false; }
bool supportsCompletion() const override { return true; }
bool loadModel(const std::string &modelPath, int n_ctx) override;
bool loadModel(const std::string &modelPath, int n_ctx, int ngl) override;
bool isModelLoaded() const override;
size_t requiredMem(const std::string &modelPath, int n_ctx) override;
size_t requiredMem(const std::string &modelPath, int n_ctx, int ngl) override;
size_t stateSize() const override;
size_t saveState(uint8_t *dest) const override;
size_t restoreState(const uint8_t *src) override;
void setThreadCount(int32_t n_threads) override;
int32_t threadCount() const override;
std::vector<GPUDevice> availableGPUDevices(size_t memoryRequired) override;
bool initializeGPUDevice(size_t memoryRequired, const std::string& name) override;
bool initializeGPUDevice(const GPUDevice &device, std::string *unavail_reason) override;
bool initializeGPUDevice(int device) override;
std::vector<GPUDevice> availableGPUDevices(size_t memoryRequired) const override;
bool initializeGPUDevice(size_t memoryRequired, const std::string& name) const override;
bool initializeGPUDevice(int device, std::string *unavail_reason) const override;
bool hasGPUDevice() override;
bool usingGPUDevice() override;
private:
LLamaPrivate *d_ptr;
std::unique_ptr<LLamaPrivate> d_ptr;
protected:
std::vector<Token> tokenize(PromptContext &, const std::string&) const override;
@@ -42,6 +42,9 @@ protected:
bool evalTokens(PromptContext& ctx, const std::vector<int32_t> &tokens) const override;
int32_t contextLength() const override;
const std::vector<Token>& endTokens() const override;
int32_t maxContextLength(std::string const &modelPath) const override;
int32_t layerCount(std::string const &modelPath) const override;
};
#endif // LLAMAMODEL_H