Another silly excuses. Google Turboquat allows for 4x compression of context ONLY, Think of LLM is the memory and knowledge of a expert. Context is basically length of the question you can ask. Longer context is good and context compression is great, but it will just make local models more useable and not reduce the need for more memory and bigger models.
# SanDisk & Micron Back: Is Memory Bull Trend Still Here?

Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.

Report

Comment

  • Top
  • Latest
empty
No comments yet