Groq Sets New Large Language Model Performance Record of 300 Tokens per Second per User on Meta AI Foundational LLM, Llama-2 70B
Groq Sets New Large Language Model Performance Record of 300 Tokens per Second per User on Meta AI Foundational LLM, Llama-2 70B
Groq 在 Meta AI Foundational LLM、Llama-2 70B 上創下了每位用戶每秒 300 個代幣的新大型語言模型性能記錄
- The Groq Language Processing Unit system is the AI assistance enablement technology poised to provide real-time, "low lag" experiences for users with its inference performance.
- Groq 語言處理單元系統是一項 AI 輔助支持技術，可憑藉其推理性能爲用戶提供實時、“低延遲” 的體驗。
MOUNTAIN VIEW, Calif., Nov. 7, 2023 /PRNewswire/ -- Groq, an AI solutions company, announced it still holds the foundational Large Language Model (LLM) performance record for speed and accuracy amidst emerging market competition. Groq has set a new performance bar of more than 300 tokens per second per user on Meta AI's industry-leading LLM, Llama-2 70B, run on its Language Processing Unit system.
加利福尼亞州山景城， 2023年11月7日 /PRNewswire/ — Groq一家人工智能解決方案公司宣佈，在新興市場競爭中，它在速度和準確性方面仍保持基本的大語言模型（LLM）性能記錄。Groq 在 Meta AI 行業領先的 LLM Llama-2 上設定了每位用戶每秒 300 多個代幣的新性能標準 70B，在其語言處理單元系統上運行。