Quantized Neural Network Inference with Precision Batching
원문 초록
We present PrecisionBatching, a quantized inference algorithm for speeding up neural network execution on traditional hardware platforms at low bitwidths without the need for retraining or recalibration. PrecisionBatching decomposes a neural network into individual bitlayers and accumulates them using fast 1-bit operations while maintaining activations in full precision. PrecisionBatching not only facilitates quantized inference at low bitwidths (< 8 bits) without the need for retraining/recalibration, but also 1) enables traditional hardware platforms the ability to realize inference speedups at a finer granularity of quantization (e.g: 1-16 bit execution) and 2) allows accuracy and speedup tradeoffs at runtime by exposing the number of bitlayers to accumulate as a tunable parameter. Across a variety of applications (MNIST, language modeling, natural language inference) and neural network architectures (fully connected, RNN, LSTM), PrecisionBatching yields end-to-end speedups of over 8x on a GPU within a < 1% error margin of the full precision baseline, outperforming traditional 8-bit quantized inference by over 1.5x-2x at the same error tolerance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification
Parameter Efficient Fine Tuning Llama 3.1 for Answering Arabic Legal Questions: A Case Study on Jordanian Laws
DIBERT: Dependency Injected Bidirectional Encoder Representations from Transformers
Specification-based Security Evaluation of Real-World Agents Tool-Calling under Long-Horizon Context Tasks
Making Language Model a Hierarchical Classifier and Generator
토론
이 논문과 연결된 포럼 글이 아직 없습니다.