Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization
Large Language Models (LLMs) are proficient in natural language processing tasks, but their deployment is often restricted by extensive parameter sizes and computational demands. This paper focuses on post-training quantization (PTQ) in LLMs, specifically 4-bit weight and 8-bit activation (W4A8) quantization, to enhance computational efficiency -- a topic less explored compared to weight-only quantization. We present two innovative techniques: activation-quantization-aware scaling (AQAS) and sequence-length-aware calibration (SLAC) to enhance PTQ by considering the combined effects on weights and activations and aligning calibration sequence lengths to target tasks. Moreover, we introduce dINT, a hybrid data format combining integer and denormal representations, to address the underflow issue in W4A8 quantization, where small values are rounded to zero. Through rigorous evaluations of LLMs, including OPT and LLaMA, we demonstrate that our techniques significantly boost task accuracies to levels comparable with full-precision models. By developing arithmetic units compatible with dINT, we further confirm that our methods yield a 2$\times$ hardware efficiency improvement compared to 8-bit integer MAC unit.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyQuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
As large language models (LLMs) play an increasingly important role in code generation, enhancing both correctness and efficiency has become crucial. Current methods primarily focus on correctness, often overlooking effi…
Code GenerationArchitectural Fusion Through Contextual Partitioning in Large Language Models: A Novel Approach to Parameterized Knowledge Integration
Contextual Partitioning introduces an innovative approach to enhancing the architectural design of large-scale computational models through the dynamic segmentation of parameters into context-aware regions. This methodol…
Computational EfficiencyTALL -- A Trainable Architecture for Enhancing LLM Performance in Low-Resource Languages
Large Language Models (LLMs) excel in high-resource languages but struggle with low-resource languages due to limited training data. This paper presents TALL (Trainable Architecture for Enhancing LLM Performance in Low-R…
Computational EfficiencyTranslationHyperRAG: Enhancing Quality-Efficiency Tradeoffs in Retrieval-Augmented Generation with Reranker KV-Cache Reuse
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing the performance of large language models (LLMs) by integrating external knowledge into the generation process. A key component of RAG …
DecoderRAGRetrieval-augmented GenerationMegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production
We present MegaScale-MoE, a production system tailored for the efficient training of large-scale mixture-of-experts (MoE) models. MoE emerges as a promising architecture to scale large language models (LLMs) to unprecede…
Mixture-of-Experts