🚀 The feature, motivation and pitch
Motivation
The current UCM integration with SGLang still depends on a version-specific patch originally built for SGLang 0.5.5 (sglang-adapt.patch). This makes it hard to keep up with the latest main branch and adds unnecessary friction for users.
We want to move to a patch-free integration model for SGLang:
- use UCM as a HiCache L3 storage backend on the latest SGLang
main
- avoid modifying any SGLang source code
- make the integration available by installing UCM only
Ongoing Work
Todo PR:
PR1 (code): #886
PR2 (docs): #891
Alternatives
No response
Additional context
No response
🚀 The feature, motivation and pitch
Motivation
The current UCM integration with SGLang still depends on a version-specific patch originally built for SGLang
0.5.5(sglang-adapt.patch). This makes it hard to keep up with the latestmainbranch and adds unnecessary friction for users.We want to move to a patch-free integration model for SGLang:
mainOngoing Work
Todo PR:
PR1 (code): #886
UnifiedCacheStoreimplementation for SGLang HiCache L3dynamicbackend to registerunifiedcachePR2 (docs): #891
Alternatives
No response
Additional context
No response