Skip to content

DeepseekV3 models#2175

Open
ysjprojects wants to merge 64 commits into
mainfrom
deepseek-models
Open

DeepseekV3 models#2175
ysjprojects wants to merge 64 commits into
mainfrom
deepseek-models

Conversation

@ysjprojects
Copy link
Copy Markdown
Collaborator

TODO:

  • Test loading finegrained_fp8 weights from pretrained DeepseekV3 models
  • Run test_model_deepseek_v3.py
  • Add support for more pretrained models in the DeepseekV3 family (Deepseek-R1-0528, etc.)
  • Add prompt template support for DeepseekV3 models

@bhimrazy bhimrazy marked this pull request as draft January 8, 2026 06:53
ysjprojects and others added 21 commits February 7, 2026 20:09
@ysjprojects ysjprojects marked this pull request as ready for review March 21, 2026 16:39
@ysjprojects ysjprojects changed the title (WIP) DeepseekV3 models DeepseekV3 models Mar 25, 2026
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.

1 participant