AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

differentiate between init failure and unsupported models

Browse Source
This commit is contained in:
Cebtenzzre 2023-10-04 15:51:46 -04:00 committed by Adam Treat
parent a5b93cf095
commit 672cb850f9
4 changed files with 24 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
gpt4all-backend/llamamodel.cpp
View File

@ -301,8 +301,9 @@ bool LLamaModel::initializeGPUDevice(size_t memoryRequired, const std::string& d
#endif
}
bool LLamaModel::initializeGPUDevice(const LLModel::GPUDevice &device)
bool LLamaModel::initializeGPUDevice(const LLModel::GPUDevice &device, std::string *unavail_reason)
{
bool result = false;
#if defined(GGML_USE_KOMPUTE)
ggml_vk_device vkDevice;
vkDevice.index = device.index;
@ -310,10 +311,16 @@ bool LLamaModel::initializeGPUDevice(const LLModel::GPUDevice &device)
vkDevice.heapSize = device.heapSize;
vkDevice.name = device.name;
vkDevice.vendor = device.vendor;
return ggml_vk_init_device(vkDevice);
result = ggml_vk_init_device(vkDevice);
if (!result && unavail_reason) {
*unavail_reason = "failed to init device";
}
#else
return false;
if (unavail_reason) {
*unavail_reason = "built without kompute";
}
#endif
return result;
}
bool LLamaModel::initializeGPUDevice(int device)

2
gpt4all-backend/llamamodel_impl.h
View File

@ -27,7 +27,7 @@ public:
int32_t threadCount() const override;
std::vector<GPUDevice> availableGPUDevices(size_t memoryRequired) override;
bool initializeGPUDevice(size_t memoryRequired, const std::string& device) override;
bool initializeGPUDevice(const GPUDevice &device) override;
bool initializeGPUDevice(const GPUDevice &device, std::string *unavail_reason) override;
bool initializeGPUDevice(int device) override;
bool hasGPUDevice() override;
bool usingGPUDevice() override;

7
gpt4all-backend/llmodel.h
View File

@ -97,7 +97,12 @@ public:
virtual std::vector<GPUDevice> availableGPUDevices(size_t /*memoryRequired*/) { return std::vector<GPUDevice>(); }
virtual bool initializeGPUDevice(size_t /*memoryRequired*/, const std::string& /*device*/) { return false; }
virtual bool initializeGPUDevice(const GPUDevice &/*device*/) { return false; }
virtual bool initializeGPUDevice(const GPUDevice &/*device*/, std::string *unavail_reason = nullptr) {
if (unavail_reason) {
*unavail_reason = "unsupported model type";
}
return false;
}
virtual bool initializeGPUDevice(int /*device*/) { return false; }
virtual bool hasGPUDevice() { return false; }
virtual bool usingGPUDevice() { return false; }

10
gpt4all-chat/chatllm.cpp
View File

@ -282,11 +282,14 @@ bool ChatLLM::loadModel(const ModelInfo &modelInfo)
}
}
if (!device || !m_llModelInfo.model->initializeGPUDevice(*device)) {
emit reportFallbackReason("<br>Using CPU: failed to init device");
emit reportFallbackReason(""); // no fallback yet
std::string unavail_reason;
if (!device) {
// GPU not available
} else if (!m_llModelInfo.model->initializeGPUDevice(*device, &unavail_reason)) {
emit reportFallbackReason(QString::fromStdString("<br>Using CPU: " + unavail_reason));
} else {
actualDevice = QString::fromStdString(device->name);
emit reportFallbackReason(""); // no fallback yet
}
}
@ -306,6 +309,7 @@ bool ChatLLM::loadModel(const ModelInfo &modelInfo)
// We might have had to fallback to CPU after load if the model is not possible to accelerate
// for instance if the quantization method is not supported on Vulkan yet
emit reportDevice("CPU");
// TODO(cebtenzzre): report somewhere if llamamodel decided the model was not supported
emit reportFallbackReason("<br>Using CPU: unsupported quantization type");
}