alt Hacker NewsFor the most part each provider implemented their own inference engines. This release will help them all adopt the common set of optimisations to serve DeepSeek Flash optimally.
Replies
shafyy • today at 12:38 PM
Interesting, thanks!
For the most part each provider implemented their own inference engines. This release will help them all adopt the common set of optimisations to serve DeepSeek Flash optimally.
Interesting, thanks!
Well except that baseten serves deepseek faster than this already at a lower price. So this seems to mostly help startup inference providers that don't have their own inference engines.