Merge pull request #94591 from mletalie/OSDOCS-10294

[OSDOCS-10294]Documentation for inf/trn instances

Author: bmcelvee

modules/rosa-sdpolicy-am-aws-compute-types.adoc

@@ -340,6 +340,30 @@
 
 Support for the GPU instance type software stack is provided by AWS. Ensure that your AWS service quotas can accommodate the desired GPU instance types.
 ====
+
+.Accelerated computing - AWS Trainium and Inferentia
+[%collapsible]
+====
+[WARNING]
+--
+For more information about AWS Trainium and Inferentia instance types, see link:https://access.redhat.com/articles/7117097[Inferentia & Trainium instances on ROSA].
+--
+
+- trn1.2xlarge (8 vCPU, 32 GiB)
+- trn1.32xlarge (128 vCPU, 512 GiB)
+- trn1n.32xlarge (128 vCPU, 512 GiB)
+- trn2.48xlarge (192 vCPU, 2048 GiB)
+- trn2u.48xlarge (192 vCPU, 2048 GiB)
+- inf1.xlarge (4 vCPU, 8 GiB)
+- inf1.2xlarge (8 vCPU, 16 GiB)
+- inf1.6xlarge (24 vCPU, 48 GiB)
+- inf1.24xlarge (96 vCPU, 192 GiB)
+- inf2.xlarge (4 vCPU, 16 GiB)
+- inf2.8xlarge (32 vCPU, 128 GiB)
+- inf2.24xlarge (96 vCPU, 384 GiB)
+- inf2.48xlarge (192 vCPU, 768 GiB)
+====
+
 .Compute optimized
 [%collapsible]
 ====