Peaked at #1 Off the board
DeepSeek Open Sources DeepGEMM
DeepSeek open-sources DeepGEMM, claiming up to 98% token savings by yielding more tokens per GPU and cutting costs.
Key points
- DeepSeek released DeepGEMM, a library it uses to train and run its own models.
- The library is said to save up to 98% on tokens, and to let users pay $1.6 instead of $50.
- It is available in one public repo, with a link below the post.
Key points and the reaction summary are written by AI from the posts on this page. Check the original post. How we use AI
Original post
China f*cked the world again
DeepSeek just dropped a killer library that saves up to 98% on tokens ur GPT Astra and Opus 5.5
it's DeepGEMM, the engine DeepSeek trains and runs its own models on
faster GPU math -> more tokens per GPU -> cheaper tokens
> plug the engine DeepSeek uses into your own models
> squeeze more tokens per second out of the GPUs you already pay for
> match or beat expert-tuned GPU libraries on speed
u will pay $1.6 instead of $50
its sitting in one public repo, link below
Top replies on X
Sign in to see 5 top replies from X
From @GrowthRL, @cyprianzube, @noodlesinmysand and others. Spam removed, with English and Chinese translations.
Discussion 0
Sign up Sign in to join the discussion
No comments yet. Start the conversation.