|
1 | 1 | <p align="center">
|
2 | 2 | <picture>
|
3 |
| - <source media="(prefers-color-scheme: dark)" srcset="https://github.com/neuralmagic/guidellm/blob/main/docs/assets/guidellm-logo-light.png"> |
4 |
| - <img alt="GuideLLM Logo" src="https://github.com/neuralmagic/guidellm/blob/main/docs/assets/guidellm-logo-dark.png" width=55%> |
| 3 | + <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/neuralmagic/guidellm/main/docs/assets/guidellm-logo-light.png"> |
| 4 | + <img alt="GuideLLM Logo" src="https://raw.githubusercontent.com/neuralmagic/guidellm/main/docs/assets/guidellm-logo-dark.png" width=55%> |
5 | 5 | </picture>
|
6 | 6 | </p>
|
7 | 7 |
|
8 | 8 | <h3 align="center">
|
9 | 9 | Scale Efficiently: Evaluate and Optimize Your LLM Deployments for Real-World Inference
|
10 | 10 | </h3>
|
11 | 11 |
|
12 |
| -[](https://github.com/neuralmagic/guidellm/releases) [](https://github.com/neuralmagic/guidellm/tree/main/docs) [](https://github.com/neuralmagic/guidellm/blob/main/LICENSE) [](https://pypi.python.org/pypi/guidellm) [](https://pypi.python.org/pypi/guidellm-nightly) [](https://pypi.python.org/pypi/guidellm) [](https://github.com/neuralmagic/guidellm/actions/workflows/nightly.yml) |
| 12 | +[](https://github.com/neuralmagic/guidellm/releases) [](https://github.com/neuralmagic/guidellm/tree/main/docs) [](https://github.com/neuralmagic/guidellm/blob/main/LICENSE) [](https://pypi.python.org/pypi/guidellm) [](https://pypi.python.org/pypi/guidellm-nightly) [](https://pypi.python.org/pypi/guidellm) [](https://github.com/neuralmagic/guidellm/actions/workflows/nightly.yml) |
13 | 13 |
|
14 | 14 | ## Overview
|
15 | 15 |
|
16 | 16 | <p>
|
17 | 17 | <picture>
|
18 |
| - <source media="(prefers-color-scheme: dark)" srcset="https://github.com/neuralmagic/guidellm/blob/main/docs/assets/guidellm-user-flows-dark.png"> |
19 |
| - <img alt="GuideLLM User Flows" src="https://github.com/neuralmagic/guidellm/blob/main/docs/assets/guidellm-user-flows-light.png"> |
| 18 | + <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/neuralmagic/guidellm/main/docs/assets/guidellm-user-flows-dark.png"> |
| 19 | + <img alt="GuideLLM User Flows" src="https://raw.githubusercontent.com/neuralmagic/guidellm/main/docs/assets/guidellm-user-flows-light.png"> |
20 | 20 | </picture>
|
21 | 21 | </p>
|
22 | 22 |
|
@@ -84,11 +84,11 @@ After the evaluation is completed, GuideLLM will summarize the results, includin
|
84 | 84 |
|
85 | 85 | The output results will start with a summary of the evaluation, followed by the requests data for each benchmark run. For example, the start of the output will look like the following:
|
86 | 86 |
|
87 |
| -<img alt="Sample GuideLLM benchmark start output" src="https://github.com/neuralmagic/guidellm/blob/main/docs/assets/sample-output-start.png" /> |
| 87 | +<img alt="Sample GuideLLM benchmark start output" src="https://raw.githubusercontent.com/neuralmagic/guidellm/main/docs/assets/sample-output-start.png" /> |
88 | 88 |
|
89 | 89 | The end of the output will include important performance summary metrics such as request latency, time to first token (TTFT), inter-token latency (ITL), and more:
|
90 | 90 |
|
91 |
| -<img alt="Sample GuideLLM benchmark end output" src="https://github.com/neuralmagic/guidellm/blob/main/docs/assets/sample-output-end.png" /> |
| 91 | +<img alt="Sample GuideLLM benchmark end output" src="https://raw.githubusercontent.com/neuralmagic/guidellm/main/docs/assets/sample-output-end.png" /> |
92 | 92 |
|
93 | 93 | #### 4. Use the Results
|
94 | 94 |
|
|
0 commit comments