[GH-ISSUE #415] Does vLLM support offloading the weights of the DeepSeek R1 model to the CPU during large model inference? #326

Closed
opened 2026-10-26 21:19:28 +00:00 by bsakaguchi · 1 comment
Owner

Originally created by @BigCousin-z on GitHub (Feb 15, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/415

Does vLLM support offloading the weights of the DeepSeek R1 model to the CPU during large model inference?

Originally created by @BigCousin-z on GitHub (Feb 15, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/415 Does vLLM support offloading the weights of the DeepSeek R1 model to the CPU during large model inference?
Author
Owner

@mowentian commented on GitHub (Feb 18, 2025):

请移步 vllm 社区以寻求支持

<!-- gh-comment-id:2665141921 --> @mowentian commented on GitHub (Feb 18, 2025): 请移步 vllm 社区以寻求支持
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-R1#326
No description provided.