mirror of
https://github.com/kvcache-ai/Mooncake.git
synced 2026-11-05 01:17:55 +00:00
[GH-ISSUE #34] Mooncake Transfer Engine 支持华为的Ascend昇腾平台和NPU显卡吗 #19
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#19
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 @zhaofangtao on GitHub (Dec 13, 2024).
Original GitHub issue: https://github.com/kvcache-ai/Mooncake/issues/34
看doc文档,需要配置cuda环境。 现在算力资源都在国产化,请问Mooncake Transfer Engine 能适配华为的Ascend昇腾平台和NPU显卡吗?
@alogfans commented on GitHub (Dec 13, 2024):
Mooncake 适配国产化算力设备是未来工作的一个重要部分。Transfer Engine 自身支持 RoCE/eRDMA 等网络,因此可使用国产设备部署。CUDA 用于实现 GPU VRAM 数据直传远程 DRAM 功能,该功能需使用 GPUDirect RDMA。如果国产卡有类似的功能接口可以移植。也可以由用户自行实现经本地 DRAM 中转将数据传到远程 DRAM(多一次拷贝),这种模式下不需要开启 USE_CUDA 开关。