chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

docs: defer CP HiCache performance follow-up

Browse Source
This commit is contained in:
谢骞
2026-05-08 03:07:18 +08:00
parent 9617d52639
commit eecc8e21ec
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
docs/superpowers/specs/2026-05-07-cp-hicache-host-design.md
View File

@@ -427,3 +427,12 @@ These items are deliberately deferred:
- Independent CP-specific host ratio configuration.
- Decode-side CP/shared KV HiCache support.
- Upstream UnifiedRadixTree or HybridCacheController migration.
## Deferred Performance Follow-Up
After host-only CP HiCache correctness lands, port HiCache performance work from
`25b6a957c` as separate changes with their own tests. Split cached timestamp use,
incremental eviction heap maintenance, persistent all-reduce tensors, and async
write acknowledgement into independent patches. Each patch must preserve CP
zero-owned write/load no-op acknowledgement cardinality and must rerun the CP
HiCache unit regression commands from the implementation plan.