Li Ming

Results 2 issues of Li Ming

I used onnx package load my llm model directly successfully in my ubuntu x86 platform. `model = onnx.load("Qwen_models/Qwen-7B-onnx/qwen_model.onnx") for node in model.graph.node: print(node.op_type) pass` but failed with `optimum`,my code is...

bug
onnxruntime
onnx

Can I use Optimum-benchmark to evaluate the performance of qwen.cpp or llama.cpp?