SemanticScuttle - klotz.me

Tags: context* + chat*

0 bookmark(s) - Sort by: Date ↓ / Title /

1. StreamingLLM (llama.cpp & llamacpp_HF loaders)

   This PR implements the StreamingLLM technique for model loaders, focusing on handling context length and optimizing chat generation speed.

   2024-11-26 Tags: streamingllm, llama.cpp, context, chat, llm, oobabooga by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0