mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-11-05 01:07:28 +00:00
[GH-ISSUE #125] Considering Q4 introduces high PPL, does ktransfomers support official claimed F8 for 671B? #68
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
kvcache-ai/ktransformers#68
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 @ghostplant on GitHub (Feb 10, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/125
Considering Q4 introduces high PPL, does ktransfomers support official claimed F8 for 671B? What's the token generation speed?
@chenht2022 commented on GitHub (Feb 10, 2025):
Good Insight! But at this point, we only support and test Q4 and Q8. We will consider to add your recommended feature in the future.
@ghostplant commented on GitHub (Feb 10, 2025):
OK, by the way, may I know what the GPU type it is used by? https://github.com/kvcache-ai/ktransformers?tab=readme-ov-file#-show-cases
@Azure-Tang commented on GitHub (Feb 11, 2025):
4090d
@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!