deepseek-ai/DeepSeek-MoE
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-MoE.git synced 2026-11-05 00:57:43 +00:00
Code Issues 24 Projects Packages Wiki Activity

[GH-ISSUE #13] deepseek-moe-16b inference speed is slower than Baichuan-13b #10

New issue
Closed
opened 2026-10-26 21:01:37 +00:00 by bsakaguchi · 3 comments
bsakaguchi commented 2026-10-26 21:01:37 +00:00
Owner
Copy link

Originally created by @ifromeast on GitHub (Jan 18, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-MoE/issues/13

Hi, I have tested inference performance of deepseek-moe-16b and baichuan-13b on A800-80G, the result is

deepseek-moe-16b 14.73 tokens/s
baichuan-13b 22.00 tokens/s

Is the result in line with expectations？ Or is there anything wrong with me ?

Originally created by @ifromeast on GitHub (Jan 18, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-MoE/issues/13 Hi, I have tested inference performance of deepseek-moe-16b and baichuan-13b on A800-80G, the result is ``` deepseek-moe-16b 14.73 tokens/s baichuan-13b 22.00 tokens/s ``` Is the result in line with expectations？ Or is there anything wrong with me ?
bsakaguchi commented 2026-10-26 21:01:38 +00:00
Author
Owner
Copy link

@zwd003 commented on GitHub (Jan 19, 2024):

you can try with this https://github.com/vllm-project/vllm/pull/2453

<!-- gh-comment-id:1899633996 --> @zwd003 commented on GitHub (Jan 19, 2024): you can try with this https://github.com/vllm-project/vllm/pull/2453
bsakaguchi commented 2026-10-26 21:01:38 +00:00
Author
Owner
Copy link

@ifromeast commented on GitHub (Jan 19, 2024):

Have you tested the performance and comparison of deepseek-moe-16b and dense 13B model under the same environment?

<!-- gh-comment-id:1899998589 --> @ifromeast commented on GitHub (Jan 19, 2024): Have you tested the performance and comparison of deepseek-moe-16b and dense 13B model under the same environment?
bsakaguchi commented 2026-10-26 21:01:38 +00:00
Author
Owner
Copy link

@zwd003 commented on GitHub (Jan 23, 2024):

Have you tested the performance and comparison of deepseek-moe-16b and dense 13B model under the same environment?

now, it's faster than 7b, see link above

<!-- gh-comment-id:1905444240 --> @zwd003 commented on GitHub (Jan 23, 2024): > Have you tested the performance and comparison of deepseek-moe-16b and dense 13B model under the same environment? now, it's faster than 7b, see link above
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

  
WIP
No labels
pull-request
WIP
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
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-MoE#10
No description provided.