|
|
|
|
|
|
by SwellJoe
9 days ago
|
|
|
Nobody does caching as well as DeepSeek, so I guess it's a big enough difference in the implementation to make it difficult. If you use Reasonix with DeepSeek it gets silly, as it is append-only to work with how caching works. It gets something like 97-98% cached tokens in a long session. It makes an already cheap model even cheaper. |
|
|