mirror of
https://github.com/kvcache-ai/Mooncake.git
synced 2026-11-05 01:17:55 +00:00
[GH-ISSUE #295] mooncake 默认构建没开USE_CUDA,怎么池化管理DRAM/VRAM/DISK内存的? #117
Labels
No labels
ascend
auto-closed
bug
bug
CI/Build
Common
documentation
enhancement
feature request
good first issue
help wanted
high priority
MetaX
nightly-failure
pull-request
PyTorch Backend
question
RFC
Roadmap
stale
Store
Tests
Transfer Engine
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
kvcache-ai/Mooncake#117
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 @zhaotyer on GitHub (Apr 23, 2025).
Original GitHub issue: https://github.com/kvcache-ai/Mooncake/issues/295
看vllm中的实现
只申请了部分cpu memory,没有池化管理DRAM/VRAM/DISK内存
@alogfans commented on GitHub (Apr 25, 2025):
Currently Mooncake Store uses DRAM-based memory pool. For VRAM-based memory pool, since the VRAM space is limited, we think that it's better to manage VRAM KVCache per node (i.e., not interconnected). We are also working at the support of SSD-based tiered caching. Stay tuned!
@github-actions[bot] commented on GitHub (Jul 14, 2026):
This issue has had no activity for 90 days and will be closed in 7 days if there is no further activity. Please comment or react if it should stay open.
@github-actions[bot] commented on GitHub (Jul 21, 2026):
Closing due to 3 months of inactivity. If this is still relevant, please comment and we can reopen.