-
Notifications
You must be signed in to change notification settings - Fork 94
Pull requests: ModelEngine-Group/unified-cache-management
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Bugfix] Propagate shared cache load failures
#1158
opened Jul 25, 2026 by
dante159753
Contributor
•
Draft
[Feat] Support GLM 5.2 layerwise for cuda
#1157
opened Jul 25, 2026 by
flesher0813
Contributor
Loading…
[Refactor] Decouple HLA-specific params from UCMDirectConnector._crea…
#1154
opened Jul 24, 2026 by
sumingZero
Contributor
Loading…
[Feat] Add DramPool completion poller
#1150
opened Jul 23, 2026 by
yumingyue624
Contributor
Loading…
[Feat] Add Metrics View cache hit rate presets
#1149
opened Jul 23, 2026 by
dante159753
Contributor
Loading…
[WIP] [Feat] Add asynchronous buffer delegator executor
#1148
opened Jul 23, 2026 by
pyxyzc
Contributor
Loading…
[Feat] AsuStore adds configurations of device_ip
#1147
opened Jul 23, 2026 by
Fengli5355
Contributor
Loading…
[docs] add supported models, versions
#1142
opened Jul 22, 2026 by
Lijiachen1018
Contributor
Loading…
[Feat] AsuClient modifies the process of registration
#1135
opened Jul 21, 2026 by
Fengli5355
Contributor
Loading…
[Opt] Use 2 stores to dump/load dsa for sglang v0.5.14
#1122
opened Jul 18, 2026 by
flesher0813
Contributor
Loading…
Add a No-I/O Inference Duration Monitoring Connector
#1118
opened Jul 17, 2026 by
snoopyri
Contributor
Loading…
[BugFix] Fix MTP speculative decoding and multi-group load failure recovery for HLA connector
#1112
opened Jul 16, 2026 by
sumingZero
Contributor
Loading…
[Feat] Add DRAM pool KV protocol with unified pack/unpack
#1040
opened Jun 22, 2026 by
yumingyue624
Contributor
Loading…
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.