Azure
/
AzurePublicDataset
зеркало из https://github.com/Azure/AzurePublicDataset.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность

Update README.md to add LLM 2024 traces

This commit is contained in:
Inigo Goiri 2024-09-10 17:46:51 -07:00 коммит произвёл GitHub
Родитель 387b4bcb00
Коммит 84a4892dc2
Не найден ключ, соответствующий данной подписи
Идентификатор ключа GPG: B5690EEEBB952194
1 изменённых файлов: 1 добавлений и 0 удалений
Показать статистику Скачать Patch файл Скачать Diff файл Показать все файлы Свернуть все файлы

1
README.md
Просмотреть файл

@ -69,6 +69,7 @@ If you do use the Azure Functions 2021 trace in your research, please cite this
## Azure LLM Inference Traces ## Azure LLM Inference Traces
* [AzureLLMInferenceDataset2023](https://github.com/Azure/AzurePublicDataset/blob/master/AzureLLMInferenceDataset2023.md) - This is a sample of two LLM inference services in Azure containing the input and output tokens. This dataset was collected on November 11<sup>th</sup> 2023. This contains the data described and analyzed in the ISCA 2024 paper 'Splitwise: Efficient generative LLM inference using phase splitting'. * [AzureLLMInferenceDataset2023](https://github.com/Azure/AzurePublicDataset/blob/master/AzureLLMInferenceDataset2023.md) - This is a sample of two LLM inference services in Azure containing the input and output tokens. This dataset was collected on November 11<sup>th</sup> 2023. This contains the data described and analyzed in the ISCA 2024 paper 'Splitwise: Efficient generative LLM inference using phase splitting'.
* [AzureLLMInferenceDataset2024](https://github.com/Azure/AzurePublicDataset/blob/master/AzureLLMInferenceDataset2024.md) - This is a longer one week sample of two LLM inference services in Azure containing the input and output tokens. This dataset was collected on May 2024. This contains the data described and analyzed in the arxiv paper 'DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency'.
### Contact us ### Contact us
Please let us know of any issues or questions by sending email to our [mailing list](mailto:azurepublicdataset@service.microsoft.com). Please let us know of any issues or questions by sending email to our [mailing list](mailto:azurepublicdataset@service.microsoft.com).