Skip to content
← Back to explorer

InnerQ: Hardware-aware Tuning-free Quantization of KV Cache for Large Language Models

Sayed Mohammadreza Tayaranian Hosseini, Amir Ardakani, Warren J. Gross · Feb 26, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this paper page

Coverage: Stale

Use this page to decide whether the paper is strong enough to influence an eval design. It summarizes the abstract plus available structured metadata. If the signal is thin, use it as background context and compare it against stronger hub pages before making protocol choices.

Best use

Background context only

Metadata: Stale

Trust level

Low

Signals: Stale

What still needs checking

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Signal confidence: 0.45

Abstract

Reducing the hardware footprint of large language models (LLMs) during decoding is critical for efficient long-sequence generation. A key bottleneck is the key-value (KV) cache, whose size scales with sequence length and easily dominates the memory footprint of the model. Previous work proposed quantization methods that are focused on compressing the KV cache while maintaining its information. We introduce InnerQ, a hardware-aware KV-cache quantization scheme that lowers decode latency without sacrificing accuracy. InnerQ applies group-wise quantization while grouping the cache matrices over their inner dimension. Unlike previous work that group over the outer dimension, InnerQ aligns dequantization with the vector-matrix multiplication and enables scale factor reuse across GPU compute units. This reduces memory accesses and accelerates dequantization, yielding up to $22\%$ speedup over previous work and up to $88\%$ over half-precision vector-matrix multiplication. To preserve fidelity under aggressive compression, InnerQ incorporates (i) hybrid quantization, selecting symmetric or asymmetric quantization per group based on local statistics; (ii) high-precision windows for both the most recent tokens and the attention sink tokens to mitigate outlier leakage; and (iii) per-channel normalization of the key cache, computed once during prefill and folded into the query to avoid runtime overhead. Our evaluation experiments on Llama models shows that InnerQ maintains a few-shot GSM8K performance comparable to non-quantized KV caches and surpasses prior KV cache quantization methods.

Use caution before copying this protocol

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.45 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

5/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What This Page Found In The Paper

Each field below shows whether the signal looked explicit, partial, or missing in the available metadata. Use this to judge what is safe to trust directly and what still needs full-paper validation.

Human Feedback Types

missing

None explicit

Confidence: Low Not found

No explicit feedback protocol extracted.

Evidence snippet: Reducing the hardware footprint of large language models (LLMs) during decoding is critical for efficient long-sequence generation.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Direct evidence

Includes extracted eval setup.

Evidence snippet: Reducing the hardware footprint of large language models (LLMs) during decoding is critical for efficient long-sequence generation.

Quality Controls

missing

Not reported

Confidence: Low Not found

No explicit QC controls found.

Evidence snippet: Reducing the hardware footprint of large language models (LLMs) during decoding is critical for efficient long-sequence generation.

Benchmarks / Datasets

partial

GSM8K

Confidence: Low Direct evidence

Useful for quick benchmark comparison.

Evidence snippet: Our evaluation experiments on Llama models shows that InnerQ maintains a few-shot GSM8K performance comparable to non-quantized KV caches and surpasses prior KV cache quantization methods.

Reported Metrics

partial

Accuracy, Precision, Latency

Confidence: Low Direct evidence

Useful for evaluation criteria comparison.

Evidence snippet: We introduce InnerQ, a hardware-aware KV-cache quantization scheme that lowers decode latency without sacrificing accuracy.

Rater Population

missing

Unknown

Confidence: Low Not found

Rater source not explicitly reported.

Evidence snippet: Reducing the hardware footprint of large language models (LLMs) during decoding is critical for efficient long-sequence generation.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Math
  • Signal basis: Structured extraction plus abstract evidence.

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Signal confidence: 0.45
  • Known cautions: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

GSM8K

Reported Metrics

accuracyprecisionlatency

Research Brief

Metadata summary

Reducing the hardware footprint of large language models (LLMs) during decoding is critical for efficient long-sequence generation.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • Reducing the hardware footprint of large language models (LLMs) during decoding is critical for efficient long-sequence generation.
  • A key bottleneck is the key-value (KV) cache, whose size scales with sequence length and easily dominates the memory footprint of the model.
  • Previous work proposed quantization methods that are focused on compressing the KV cache while maintaining its information.

Researcher Actions

  • Compare this paper against others mentioning GSM8K.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

GSM8K Accuracy

Research Summary

Contribution Summary

  • We introduce InnerQ, a hardware-aware KV-cache quantization scheme that lowers decode latency without sacrificing accuracy.
  • Our evaluation experiments on Llama models shows that InnerQ maintains a few-shot GSM8K performance comparable to non-quantized KV caches and surpasses prior KV cache quantization methods.

Why It Matters For Eval

  • Our evaluation experiments on Llama models shows that InnerQ maintains a few-shot GSM8K performance comparable to non-quantized KV caches and surpasses prior KV cache quantization methods.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: GSM8K

  • Pass: Metric reporting is present

    Detected: accuracy, precision, latency

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Create Account & Post a Job
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
Learn About Managed Service
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.
Join Now