Pith. sign in

REVIEW 8 cited by

QQQ: Quality Quattuor-Bit Quantization for Large Language Models

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 2406.09904 v3 pith:YNOCU5S3 submitted 2024-06-14 cs.LG

classification cs.LG
keywords timesgemmperformancequantizationspeedw4a8inferencemodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding stages of inference. W4A8 is a promising strategy to accelerate both of them while usually leads to a significant performance degradation. To address these issues, we present QQQ, a Quality Quattuor-bit Quantization method with 4-bit weights and 8-bit activations. QQQ employs adaptive smoothing and Hessian-based compensation, significantly enhancing the performance of quantized models without extensive training. Furthermore, we meticulously engineer W4A8 GEMM kernels to increase inference speed. Our specialized per-channel W4A8 GEMM and per-group W4A8 GEMM achieve impressive speed increases of 3.67$\times$ and 3.29 $\times$ over FP16 GEMM. Our extensive experiments show that QQQ achieves performance on par with existing state-of-the-art LLM quantization methods while significantly accelerating inference, achieving speed boosts up to 2.24 $\times$, 2.10$\times$, and 1.25$\times$ compared to FP16, W8A8, and W4A16, respectively.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Studying quantization trade-offs for efficient inference deployment in machine translation

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Quantized Hy-MT2 models stay accurate at long context, but quantized EuroLLM 9B/22B models collapse (up to ~60% chrF++ drop) while W4A8/W8A8 plus 200–400-token chunking improves serving throughput.

  2. LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving

    cs.DC 2025-09 conditional novelty 6.0 of 10

    A W4A8 GEMM kernel using shift-based overflow-safe dequantization and a hardware-scheduled pipeline reports up to 2.9x speedup over prior W4A8 kernels.

  3. Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design

    cs.CL 2025-05 conditional novelty 6.0 of 10

    EAGLE-2 loses most of its speedup on 4-bit quantized LLMs, and a hierarchical draft-then-sequence scheme restores 1.31x speedup over EAGLE-2 on W4A16 Llama-3-70B.

  4. Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference

    cs.CV 2025-05 conditional novelty 6.0 of 10

    DPQ is a post-training quantization algorithm that stores weights in INT4, computes in FP8, and uses Hessian-based group-aware reordering to keep accuracy near the full-precision model.

  5. Baichuan-M2: Scaling Medical Capability with Large Verifier System

    cs.LG 2025-09 conditional novelty 5.0 of 10

    Baichuan-M2, a 32B medical LLM trained with a patient simulator and a clinical rubric generator as RL verifiers, reports state-of-the-art HealthBench scores (60.1 overall, 34.7 hard), ahead of all open-source models.

  6. CogDDN: A Cognitive Demand-Driven Navigation with Decision Optimization and Dual-Process Thinking

    cs.AI 2025-07 conditional novelty 5.0 of 10

    CogDDN uses a fast heuristic VLM paired with a slow analytic reflection process and a growing knowledge base to navigate to objects that implicitly satisfy a user's demand, with large reported gains on AI2Thor DDN benchmarks.

  7. Is (Selective) Round-To-Nearest Quantization All You Need?

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Selective round-to-nearest quantization, combined with Marlin-based kernels, matches or beats GPTQ, AWQ, and BitsAndBytes on accuracy and speed in most tested settings.

  8. Rethinking the Outlier Distribution in Large Language Models: An In-depth Study

    cs.CL 2025-05 reject novelty 4.0 of 10

    The paper claims that most massive activations in LLMs are residual-propagated 'fake' outliers that can be removed without accuracy loss.

Pith tools