# KV cache compression on 5 sequences Seq 1 (hard)

Source: [KV cache compression on 5 sequences Seq 1 (hard)](<https://www.sota2.com/research/sota/kv-cache-compression-on-5-sequences-seq-1-hard>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-31T10:31:06.555Z

Evaluation of KV cache compression performance on the specific 'Seq 1 (hard)' subset of sequences, measured by KL divergence and improvement factor.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | KV cache compression |
| Dataset (including any stated split) | 5 sequences Seq 1 (hard) |
| Metric | KL Divergence (Seq 1 hard) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [KL Divergence (Seq 1 hard)](<https://www.sota2.com/research/sota/kv-cache-compression-on-5-sequences-seq-1-hard.md?metric=KL%20Divergence%20(Seq%201%20hard)>): Lower is better; unit: SCALAR.

- [Improvement Factor (Seq 1 hard)](<https://www.sota2.com/research/sota/kv-cache-compression-on-5-sequences-seq-1-hard.md?metric=Improvement%20Factor%20(Seq%201%20hard)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | KL Divergence (Seq 1 hard) | Result date | Report paper |
| --- | --- | --- | --- |
| KVSCULPT | 0.117 | Not recorded | 69cb552e0636e5bf4afca028 |
| Select+Fit | 0.139 | Not recorded | 69cb552e0636e5bf4afca028 |

### KVSCULPT

KL Divergence (Seq 1 hard): 0.117. Result ID: 69cba11f47f34ce924b486fd.

[Reporting paper](<https://www.sota2.com/research/paper/69cb552e0636e5bf4afca028.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb552e0636e5bf4afca028.md>)

Recorded evaluation configuration: {"Compression ratio (r)":"0.3","Retain zone (m)":"256","Optimization method":"L-BFGS","Synthetic future queries":"128","V solver":"ridge regression"}. This record does not assert independent reproduction.

### Select+Fit

KL Divergence (Seq 1 hard): 0.139. Result ID: 69cba11f47f34ce924b486fc.

[Reporting paper](<https://www.sota2.com/research/paper/69cb552e0636e5bf4afca028.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a91.md>)

Recorded evaluation configuration: {"Compression ratio (r)":"0.3","Retain zone (m)":"256","V solver":"ridge regression"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
