forked from phoenix-oss/llama-stack-mirror
4dccf916d1
## What does this PR do? - Provide a distro template to let developer easily run the open benchmarks llama stack supports on llama and non-llama models. - Provide doc on how to run open benchmark eval via CLI and open benchmark contributing guide [//]: # (If resolving an issue, uncomment and update the line below) (Closes #1375 ) ## Test Plan open benchmark eval results on llama, gpt, gemini and clause <img width="771" alt="Screenshot 2025-03-06 at 7 33 05 PM" src="https://github.com/user-attachments/assets/1bd85456-b9b9-4b37-af76-4ce1d2bac00e" /> doc preview <img width="944" alt="Screenshot 2025-03-06 at 7 33 58 PM" src="https://github.com/user-attachments/assets/f4e5866d-b395-4c40-aa8b-080edeb5cdb6" /> <img width="955" alt="Screenshot 2025-03-06 at 7 34 04 PM" src="https://github.com/user-attachments/assets/629defb6-d5e4-473c-aa03-308bce386fb4" /> <img width="965" alt="Screenshot 2025-03-06 at 7 35 29 PM" src="https://github.com/user-attachments/assets/c21ff96c-9e8c-4c54-b6b8-25883125f4cf" /> <img width="957" alt="Screenshot 2025-03-06 at 7 35 37 PM" src="https://github.com/user-attachments/assets/47571c90-1381-4e2c-bbed-c4f3a60578d0" /> |
||
|---|---|---|
| .. | ||
| bedrock | ||
| cerebras | ||
| ci-tests | ||
| dell | ||
| dev | ||
| experimental-post-training | ||
| fireworks | ||
| groq | ||
| hf-endpoint | ||
| hf-serverless | ||
| meta-reference-gpu | ||
| meta-reference-quantized-gpu | ||
| nvidia | ||
| ollama | ||
| open-benchmark | ||
| passthrough | ||
| remote-vllm | ||
| sambanova | ||
| tgi | ||
| together | ||
| vllm-gpu | ||
| __init__.py | ||
| template.py | ||