🖼️00QAT vs PTQ on our edge vision model: 6 months of A/B dataDEV Community: pytorch·Marco Rinaldi·4 days ago#CF9yVI0s#dev#training#quantisation#model#int8#torch+2 more🧰Tag tools✨Add tagTL;DR: We ran post-training quantisation (PTQ) and quantisation-aware training (QAT) side by side on...15s0Read later0Read More
🖼️00TSU Protocol: An Open-Source RISC-V NPU Standard for Edge AI InferenceDEV Community·Jeffrey.Feillp·27 days ago#Mz417vDE#riscv#ai#opensource#software#hardware#open+6 more🧰Tag tools✨Add tagFrom Dev.to - opensource: TSU Protocol: An Open-Source RISC-V NPU Standard for Edge AI Inference15s0Read later0Read More
🖼️00TSU Protocol: An Open-Source RISC-V NPU Standard for Edge AI InferenceDEV Community·Jeffrey.Feillp·27 days ago#UrutDId9#riscv#ai#opensource#software#hardware#open+6 more🧰Tag tools✨Add tagFrom Dev.to - opensource: TSU Protocol: An Open-Source RISC-V NPU Standard for Edge AI Inference15s0Read later0Read More
🖼️00Part 4: Edge Deployment of an 86M Parameter Audio TransformerDEV Community·syamaner·about 1 month ago#2dIo8eGj#onnx#threshold#links#model#int8#inference+4 more🧰Tag tools✨Add tagPost 3 ended with three numbers: 97.4% test accuracy, 100% precision, 0 false positives. All of it...15s0Read later0Read More
