SplitQuant improves low-bit quantization accuracy by splitting each layer into three equivalent layers with narrower value ranges, boosting INT2 accuracy by up to 3.3 percentage points on two BERT-Tiny models.
SparseDNN: Fast Sparse Deep Learning Inference on CPUs
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
The last few years have seen gigantic leaps in algorithms and systems to support efficient deep learning inference. Pruning and quantization algorithms can now consistently compress neural networks by an order of magnitude. For a compressed neural network, a multitude of inference frameworks have been designed to maximize the performance of the target hardware. While we find mature support for quantized neural networks in production frameworks such as OpenVINO and MNN, support for pruned sparse neural networks is still lacking. To tackle this challenge, we present SparseDNN, a sparse deep learning inference engine targeting CPUs. We present both kernel-level optimizations with a sparse code generator to accelerate sparse operators and novel network-level optimizations catering to sparse networks. We show that our sparse code generator can achieve significant speedups over state-of-the-art sparse and dense libraries. On end-to-end benchmarks such as Huggingface pruneBERT, SparseDNN achieves up to 5x throughput improvement over dense inference with state-of-the-art OpenVINO. Open source library at: https://github.com/marsupialtail/sparsednn.
citation-role summary
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SplitQuant: Layer Splitting for Low-Bit Neural Network Quantization
SplitQuant improves low-bit quantization accuracy by splitting each layer into three equivalent layers with narrower value ranges, boosting INT2 accuracy by up to 3.3 percentage points on two BERT-Tiny models.