Pith. sign in

REVIEW 2 cited by

Progressive Mixed-Precision Decoding for Efficient LLM Inference

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.13461 v2 pith:JUNX4FSD submitted 2024-10-17 cs.LG cs.CL

classification cs.LGcs.CL
keywords decodingduringinferencemodelsprecisionquantizationtimesacross
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

In spite of the great potential of large language models (LLMs) across various tasks, their deployment on resource-constrained devices remains challenging due to their excessive computational and memory demands. Quantization has emerged as an effective solution by storing weights in reduced precision. However, utilizing low precisions (i.e.~2/3-bit) to substantially alleviate the memory-boundedness of LLM decoding, still suffers from prohibitive performance drop. In this work, we argue that existing approaches fail to explore the diversity in computational patterns, redundancy, and sensitivity to approximations of the different phases of LLM inference, resorting to a uniform quantization policy throughout. Instead, we propose a novel phase-aware method that selectively allocates precision during different phases of LLM inference, achieving both strong context extraction during prefill and efficient memory bandwidth utilization during decoding. To further address the memory-boundedness of the decoding phase, we introduce Progressive Mixed-Precision Decoding (PMPD), a technique that enables the gradual lowering of precision deeper in the generated sequence, together with a spectrum of precision-switching schedulers that dynamically drive the precision-lowering decisions in either task-adaptive or prompt-adaptive manner. Extensive evaluation across diverse language tasks shows that when targeting Nvidia GPUs, PMPD achieves 1.4$-$12.2$\times$ speedup in matrix-vector multiplications over fp16 models, while when targeting an LLM-optimized NPU, our approach delivers a throughput gain of 3.8$-$8.0$\times$ over fp16 models and up to 1.54$\times$ over uniform quantization approaches while preserving the output quality.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction

    quant-ph 2025-04 conditional novelty 5.0 of 10

    A multi-agent LLM framework with iterative repair and a quantum error-correction decoder improves the correctness and noise tolerance of generated Qiskit code, with structured chain-of-thought providing the largest gain.

  2. Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Squeeze10-LLM is a staged mixed-precision post-training quantization method that binarizes 80% of LLM weights, keeps 20% at 4 bits, and reports strong sub-2-bit accuracy gains over PB-LLM.

Pith tools