Skip to content
New issue

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

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

Already on GitHub? # to your account

DeepSeek V3 FP8 Support #2719

Merged
merged 14 commits into from
Jan 24, 2025
Merged

DeepSeek V3 FP8 Support #2719

merged 14 commits into from
Jan 24, 2025

Conversation

yingcanw
Copy link
Collaborator

No description provided.

yingcanw and others added 14 commits December 24, 2024 03:48
* init v3 lite feat

* fix moe topk method

* fix noaux_tc logic

* fix deepseek v3 normal rope

* refactor

* wo conversion ok debugging build

* add quantize for attn.dense

* add unified converter support

* testing unified converter

* add convert checkpoint and update docs

---------

Co-authored-by: Zeyu Wang <zeyuw@nvidia.com>
@nv-guomingz
Copy link
Collaborator

LGTM

@nv-guomingz nv-guomingz merged commit f529c1c into NVIDIA:deepseek Jan 24, 2025
# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants