Strix Halo Wiki
Attachments
History
Blame
View Source
A - Z
Changelog
Documentation
About An Otter Wiki
Toggle dark mode
Login
Menu
Home
Buyer's Guide
AI Guides
General Guides
Boards
PCs
GitHub Mirror
Discord Server
Strix Halo Toolboxes
Page Index
AI
AI Capabilities Overview
Clustering
Clustering with RDMA
Fine-tuning-eval
llamacpp-performance
llamacpp-with-ROCm
vLLM
AI
Clustering with RDMA
0490c8
Commit
0490c8
2026-08-01 16:01:05
Lorphos
: add "rdma link" commmand
AI/Clustering_with_RDMA.md
..
@@ 147,6 147,13 @@
```
So around 1.12µs which is an expected value. Great!
-
Next, follow the [AMD Strix Halo RDMA Cluster Setup Guide](https://github.com/kyuz0/amd-strix-halo-vllm-toolboxes/blob/main/rdma_cluster/setup_guide.md)
+
Verify link:
+
```
+
$ rdma link
+
link ibp195s0/1 subnet_prefix fe80:0000:0000:0000 lid 2 sm_lid 1 lmc 0 state ACTIVE physical_state LINK_UP netdev ibp195s0
+
link ibp195s0/2 subnet_prefix fe80:0000:0000:0000 lid 0 sm_lid 0 lmc 0 state DOWN physical_state POLLING netdev ibp195s0d1
+
```
+
+
Next, follow the [AMD Strix Halo RDMA Cluster Setup Guide](https://github.com/kyuz0/amd-strix-halo-vllm-toolboxes/blob/main/rdma_cluster/setup_guide.md) starting at Step 4.4.
To be continued, it's still work in progress.
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9