why什么使用连续提前开辟好的KVcache? 这样本身就引入一个比huggingface实现快的因素？ · Issue #137 · FasterDecoding/Medusa · GitHub

FasterDecoding / Medusa Public

• Notifications You must be signed in to change notification settings
• Fork 204
• Star 2.8k

• Code
• Issues 51
• Pull requests 6
• Discussions
• Actions
• Projects
• Security and quality
• Insights

Additional navigation options

why什么使用连续提前开辟好的KVcache? 这样本身就引入一个比huggingface实现快的因素？ #137

Copy link

Copy link

Open

Open

why什么使用连续提前开辟好的KVcache? 这样本身就引入一个比huggingface实现快的因素？#137

Copy link

Description

wenhaoli-xmu

opened on Jun 19, 2025

Issue body actions

谢谢

Reactions are currently unavailable

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions