mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-11-05 01:07:28 +00:00
[GH-ISSUE #196] 请问,是否支持deepseek R1的70B蒸馏版本? 尤其是长上下文的支持? #113
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
kvcache-ai/ktransformers#113
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @traddo on GitHub (Feb 13, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/196
24G显存下deepseek的4b模型只能做到16k上下文,再长就分层到cpu了,推理速度极其低下,简直惨不忍睹。
@zty381309501 commented on GitHub (Feb 13, 2025):
内存多大?推理速度怎么样
@traddo commented on GitHub (Feb 13, 2025):
4090显卡,内存128G,671b版本运行不了。
@annian101 commented on GitHub (Feb 13, 2025):
671最低三百多的内存吧
@zty381309501 commented on GitHub (Feb 13, 2025):
我目前是4卡gpu 3090 24g+ cpu 128g内存,不知道能跑671b多少精度的模型,内存插满还能增加128g内存。
@lulu2048 commented on GitHub (Feb 13, 2025):
KT不支持所有蒸馏版本,只支持MoE架构的原版
@ErvinXie commented on GitHub (Dec 11, 2025):
This issue has been automatically closed due to inactivity for 60 days.
If you believe this issue is still relevant, please feel free to reopen it with additional information or context.
Thank you for your contribution to KTransformers!
此 issue 因超过 60 天无活动而被自动关闭。
如果您认为此问题仍然存在,请随时重新打开并提供更多信息或上下文。
感谢您对 KTransformers 的贡献!