Skip to content

Implement DeepSeek V3/R1 #2745

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 8 commits into
base: main
Choose a base branch
from

Conversation

EricLBuehler
Copy link
Member

@EricLBuehler EricLBuehler commented Jan 27, 2025

  • Model
  • FP8 weight dequantize
  • Tensor parallelism

@EricLBuehler EricLBuehler changed the title Implement DeepSeek V3 Implement DeepSeek V3/R1 Jan 27, 2025
@EricLBuehler EricLBuehler marked this pull request as ready for review January 28, 2025 14:00
@zackangelo
Copy link
Contributor

Seems like most of this PR is adding the f8 dtype, perhaps worth separating that out from the deepseek model addition so its easier to review?

@AlpineVibrations
Copy link

this Would be great. And the F8 type is really helpful for other projects.

@AlpineVibrations
Copy link

it looks like the working branch is behind the main branch now. maybe the fp8 work should be pulled out. it looks like a lot of good work by @EricLBuehler

@EricLBuehler
Copy link
Member Author

Interesting idea. I'll take a look at doing that once a few other PRs are merged - specifically the Metal MM speedup one.

@AlbertMarashi
Copy link

Is this supposed to be able to support training?

@zackangelo zackangelo mentioned this pull request Jun 11, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants