# LLM Inference on Merge dataset

Source: [LLM Inference on Merge dataset](<https://www.sota2.com/research/sota/llm-inference-on-merge-dataset>)

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

Data updated: 2026-02-26T06:02:58.824Z

Evaluation of LLM Inference performance on the Merge dataset, specifically measuring Service Level Objective (SLO) attainment.

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 | LLM Inference |
| Dataset (including any stated split) | Merge dataset |
| Metric | SLO Attainment |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [SLO Attainment](<https://www.sota2.com/research/sota/llm-inference-on-merge-dataset.md?metric=SLO%20Attainment>): Higher is better; unit: PERCENT.

## Recorded results

| Method | SLO Attainment | Result date | Report paper |
| --- | --- | --- | --- |
| AugServe | 54.3 | Not recorded | 693115d6d6b0dd3342933d87 |
| AugServe | 51.3 | Not recorded | 693115d6d6b0dd3342933d87 |
| AugServe | 45.8 | Not recorded | 693115d6d6b0dd3342933d87 |
| InferCept | 28.3 | Not recorded | 693115d6d6b0dd3342933d87 |
| vLLM | 19.5 | Not recorded | 693115d6d6b0dd3342933d87 |
| InferCept | 19.1 | Not recorded | 693115d6d6b0dd3342933d87 |
| InferCept | 14.2 | Not recorded | 693115d6d6b0dd3342933d87 |
| vLLM | 13.8 | Not recorded | 693115d6d6b0dd3342933d87 |
| vLLM | 9.7 | Not recorded | 693115d6d6b0dd3342933d87 |

### AugServe

SLO Attainment: 54.3. Result ID: 6996ce165698665ec41a100e.

[Reporting paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

Recorded evaluation configuration: {"Request rate":"2.0","Model":"OPT-13B","Hardware":"H800 GPU"}. This record does not assert independent reproduction.

### AugServe

SLO Attainment: 51.3. Result ID: 6996ce165698665ec41a100f.

[Reporting paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

Recorded evaluation configuration: {"Request rate":"3.0","Model":"OPT-13B","Hardware":"H800 GPU"}. This record does not assert independent reproduction.

### AugServe

SLO Attainment: 45.8. Result ID: 6996ce165698665ec41a1010.

[Reporting paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

Recorded evaluation configuration: {"Request rate":"4.0","Model":"OPT-13B","Hardware":"H800 GPU"}. This record does not assert independent reproduction.

### InferCept

SLO Attainment: 28.3. Result ID: 6996ce165698665ec41a100b.

[Reporting paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa736b1e209131cea5c664.md>)

Recorded evaluation configuration: {"Request rate":"2.0","Model":"OPT-13B","Hardware":"H800 GPU"}. This record does not assert independent reproduction.

### vLLM

SLO Attainment: 19.5. Result ID: 6996ce165698665ec41a1008.

[Reporting paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa708c1e209131cea4ba94.md>)

Recorded evaluation configuration: {"Request rate":"2.0","Model":"OPT-13B","Hardware":"H800 GPU"}. This record does not assert independent reproduction.

### InferCept

SLO Attainment: 19.1. Result ID: 6996ce165698665ec41a100c.

[Reporting paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa736b1e209131cea5c664.md>)

Recorded evaluation configuration: {"Request rate":"3.0","Model":"OPT-13B","Hardware":"H800 GPU"}. This record does not assert independent reproduction.

### InferCept

SLO Attainment: 14.2. Result ID: 6996ce165698665ec41a100d.

[Reporting paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa736b1e209131cea5c664.md>)

Recorded evaluation configuration: {"Request rate":"4.0","Model":"OPT-13B","Hardware":"H800 GPU"}. This record does not assert independent reproduction.

### vLLM

SLO Attainment: 13.8. Result ID: 6996ce165698665ec41a1009.

[Reporting paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa708c1e209131cea4ba94.md>)

Recorded evaluation configuration: {"Request rate":"3.0","Model":"OPT-13B","Hardware":"H800 GPU"}. This record does not assert independent reproduction.

### vLLM

SLO Attainment: 9.7. Result ID: 6996ce165698665ec41a100a.

[Reporting paper](<https://www.sota2.com/research/paper/693115d6d6b0dd3342933d87.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa708c1e209131cea4ba94.md>)

Recorded evaluation configuration: {"Request rate":"4.0","Model":"OPT-13B","Hardware":"H800 GPU"}. This record does not assert independent reproduction.

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