Skip to content

Fix/deepseek openai server#1071

Merged
charlesfrye merged 2 commits intomodal-labs:mainfrom
LeTriet17:fix/deepseek_openai_server
Feb 11, 2025
Merged

Fix/deepseek openai server#1071
charlesfrye merged 2 commits intomodal-labs:mainfrom
LeTriet17:fix/deepseek_openai_server

Conversation

@LeTriet17
Copy link
Copy Markdown
Contributor


✍️ Update GPU type and context size in deepseek_openai_server.py

  • Changed GPU type from A10G to L40S for inference to leverage better performance.
  • Reduced n_ctx from 32768 to 8096 to improve stability during experiments.
  • All other settings remain unchanged.

Type of Change

  • New example
  • Example updates (Bug fixes, new features, etc.)
  • Other (changes to the codebase, but not to examples)

WayneLe17 added 2 commits February 12, 2025 05:38
Update fastapi to 0.115.8
Update sse_starlette to 2.2.1
Update pydantic to 2.10.6
Update uvicorn to 0.34.0
Update torch to 2.6.0
@charlesfrye
Copy link
Copy Markdown
Collaborator

thanks!

@charlesfrye charlesfrye merged commit 5f42066 into modal-labs:main Feb 11, 2025
5 of 6 checks passed
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.

2 participants