| ▲ | ricardobeat 9 hours ago | |
Presumably this has been in production for a while, and is one of the reasons they were able to dramatically lower prices a month ago? | ||
| ▲ | chronogram 8 hours ago | parent | next [-] | |
Yes. Section 5 talks about real-world deployment: 5.1: "The DSpark draft models are co-deployed with the preview versions of DeepSeek-V4-Flash and DeepSeek-V4-Pro"; 5.4: "MTP-1 represents the former production setup, having been superseded by DSpark two weeks following the DeepSeek-V4-preview release." | ||
| ▲ | _0ffh 9 hours ago | parent | prev [-] | |
Lookahead Sparse Attention should be playing a big role as well, as it dramatically slashes memory consumption. | ||