Microsoft와 Fireworks AI가 Microsoft Foundry에 고성능 오픈 모델 추론 서비스를 통합해 13T 토큰/일 처리량과 180K 요청/초 성능을 Azure에서 제공
Introducing Fireworks AI on Microsoft Foundry: Bringing high performance, low latency open model inference to Azure
Introducing Fireworks AI on Microsoft Foundry: Bringing high performance, low latency open model inference to Azure
Introducing HUGS - Scale your AI with Open Models