Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

KV Cache Transform Coding for Compact Storage in LLM Inference

Konrad Staniszewski, Adrian Łańcucki

Published

Nov 3, 2025

Citations

0

Trust level

Low

Usefulness score

15/100 (Low)

Extraction confidence

55% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Mar 11, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

Should you rely on this paper?

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

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

What to verify

Validate the exact study setup in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
15/100
Adjacent candidate

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

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management. KV caches can be reused across conversation turns via shared-prefix prompts that are common in iterative code editing and chat. However, stale caches consume scarce GPU memory, require offloading, or force recomputation. We present KVTC, a lightweight transform coder that compresses KV caches for compact on-GPU and off-GPU storage. Drawing on classical media compression, KVTC combines PCA-based feature decorrelation, adaptive quantization, and entropy coding. It requires only a brief initial calibration and leaves model parameters unchanged. By exploiting redundancies in KV caches, KVTC achieves up to 20$\times$ compression while maintaining reasoning and long-context accuracy, and 40$\times$ or higher for specific use cases. We test KVTC with Llama 3, Mistral NeMo, and R1-Qwen 2.5 models across benchmarks including AIME25, GSM8K, LiveCodeBench, LongBench, MATH-500, MMLU, Qasper and RULER. It consistently outperforms inference-time baselines such as token eviction, quantization, and SVD-based methods, while achieving higher compression ratios. These results support KVTC as a practical building block for memory-efficient LLM serving with reusable KV caches.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management."

Quality Controls

strong

Calibration

Calibration/adjudication style controls detected.

"It requires only a brief initial calibration and leaves model parameters unchanged."

Benchmarks / Datasets

strong

LongBench, MMLU, MATH 500, GSM8K, LiveCodeBench

Useful for quick benchmark comparison.

"We test KVTC with Llama 3, Mistral NeMo, and R1-Qwen 2.5 models across benchmarks including AIME25, GSM8K, LiveCodeBench, LongBench, MATH-500, MMLU, Qasper and RULER."

Reported Metrics

strong

Accuracy

Useful for evaluation criteria comparison.

"By exploiting redundancies in KV caches, KVTC achieves up to 20$\times$ compression while maintaining reasoning and long-context accuracy, and 40$\times$ or higher for specific use cases."

Benchmarks and datasets

LongBenchMMLUMATH-500GSM8KLiveCodeBench

Reported metrics

accuracy
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
Math, Coding
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Calibration
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management.

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

Key takeaways

  • Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management.
  • KV caches can be reused across conversation turns via shared-prefix prompts that are common in iterative code editing and chat.
  • However, stale caches consume scarce GPU memory, require offloading, or force recomputation.

Researcher actions

  • Compare this paper against others mentioning MMLU and 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

MMLU GSM8K Accuracy

Contribution summary

  • We present KVTC, a lightweight transform coder that compresses KV caches for compact on-GPU and off-GPU storage.
  • By exploiting redundancies in KV caches, KVTC achieves up to 20\times compression while maintaining reasoning and long-context accuracy, and 40\times or higher for specific use cases.
  • We test KVTC with Llama 3, Mistral NeMo, and R1-Qwen 2.5 models across benchmarks including AIME25, GSM8K, LiveCodeBench, LongBench, MATH-500, MMLU, Qasper and RULER.

Why it matters for eval

  • We test KVTC with Llama 3, Mistral NeMo, and R1-Qwen 2.5 models across benchmarks including AIME25, GSM8K, LiveCodeBench, LongBench, MATH-500, MMLU, Qasper and RULER.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    Detected: Calibration

  • Benchmark or dataset anchors are present

    Detected: LongBench, MMLU, MATH-500, GSM8K

  • Metric reporting is present

    Detected: accuracy