2 points | by awasum_yannick an hour ago
3 comments
https://news.ycombinator.com/item?id=50163277
This probably makes enterprise private inference cheaper. Wonder if this can be generalized to server other LLMs not just DeepSeek...should not be too hard
https://news.ycombinator.com/item?id=50163277
This probably makes enterprise private inference cheaper. Wonder if this can be generalized to server other LLMs not just DeepSeek...should not be too hard