4 points | by ifoster41901 3 days ago ago
2 comments
If you change reasoning during a session, LLM needs to recompute KV cache. Maybe I get it wrong, but I don't think it can save money.
[flagged]
If you change reasoning during a session, LLM needs to recompute KV cache. Maybe I get it wrong, but I don't think it can save money.
[flagged]