Streaming and longer context lengths for LLMs on Workers AI
Workers AI now supports streaming text responses for the LLM models in our catalog, including Llama-2, using server-sent events
Author
JC
Jesse, Celso
1 articles by Jesse, Celso.
1 articles by Jesse, Celso.
Workers AI now supports streaming text responses for the LLM models in our catalog, including Llama-2, using server-sent events