feat(inferencex_atom): add M4 vLLM parity suite and W1 variant

cvs/core/orchestrators/container.py

@@ -477,11 +477,16 @@ def setup_sshd(self):
             "chown -R root:root /root/.ssh",
             "bash -c 'chmod 700 /root/.ssh && chmod 600 /root/.ssh/*'",
             "mkdir -p /run/sshd",  # Create privilege separation directory for sshd
+            "bash -c 'which sshd > /dev/null 2>&1 || (apt-get update -qq && apt-get install -y -q openssh-server iproute2)'",
             "/usr/sbin/sshd -p2224",
         ]
 
+        timeouts = {
+            "bash -c 'which sshd > /dev/null 2>&1 || (apt-get update -qq && apt-get install -y -q openssh-server iproute2)'": 120,
+        }
+
         for cmd in ssh_setup_commands:
-            result = self.exec(cmd, timeout=10, detailed=True)
+            result = self.exec(cmd, timeout=timeouts.get(cmd, 10), detailed=True)
             # Check if command succeeded on all hosts
             for hostname, output in result.items():
                 if output['exit_code'] != 0:

cvs/input/cluster_file/mi300x_atom_multi.json

@@ -0,0 +1,34 @@
+{
+  "_comment": "2-node MI300X example for inferencex_atom multinode (M5). Replace mgmt_ip / node_dict with lab IPs. head_node_dict.mgmt_ip should match the rank-0 (master) node VPC IP used in params.master_addr.",
+  "orchestrator": "container",
+  "username": "{user-id}",
+  "priv_key_file": "/home/{user-id}/.ssh/id_rsa",
+  "head_node_dict": {
+    "mgmt_ip": "{head-node-ip}"
+  },
+  "env_vars": {},
+  "node_dict": {
+    "{head-node-ip}": {
+      "bmc_ip": "NA",
+      "vpc_ip": "{head-node-ip}"
+    },
+    "{worker-node-ip}": {
+      "bmc_ip": "NA",
+      "vpc_ip": "{worker-node-ip}"
+    }
+  },
+  "container": {
+    "lifetime": "per_run",
+    "image": "rocm/atom-dev:latest",
+    "name": "inferencex_atom_mi300x_multi",
+    "runtime": {
+      "name": "docker",
+      "args": {
+        "network": "host",
+        "ipc": "host",
+        "privileged": true,
+        "shm_size": "128G"
+      }
+    }
+  }
+}

cvs/input/cluster_file/mi300x_atom_single.json

@@ -1,5 +1,5 @@
 {
-  "_comment": "Single-node MI300X example for inferencex_atom_single (ATOM driver). Replace mgmt_ip / node_dict with lab IPs.",
+  "_comment": "Single-node MI300X example for inferencex_atom (ATOM driver). Replace mgmt_ip / node_dict with lab IPs.",
   "orchestrator": "container",
   "username": "{user-id}",
   "priv_key_file": "/home/{user-id}/.ssh/id_rsa",

cvs/input/cluster_file/mi355x_atom_multi.json

@@ -0,0 +1,34 @@
+{
+  "_comment": "2-node MI355X example for inferencex_atom multinode (M5). Replace mgmt_ip / node_dict with lab IPs. head_node_dict.mgmt_ip should match the rank-0 (master) node VPC IP used in params.master_addr.",
+  "orchestrator": "container",
+  "username": "{user-id}",
+  "priv_key_file": "/home/{user-id}/.ssh/id_rsa",
+  "head_node_dict": {
+    "mgmt_ip": "{head-node-ip}"
+  },
+  "env_vars": {},
+  "node_dict": {
+    "{head-node-ip}": {
+      "bmc_ip": "NA",
+      "vpc_ip": "{head-node-ip}"
+    },
+    "{worker-node-ip}": {
+      "bmc_ip": "NA",
+      "vpc_ip": "{worker-node-ip}"
+    }
+  },
+  "container": {
+    "lifetime": "per_run",
+    "image": "rocm/atom-dev:nightly_202606211542",
+    "name": "inferencex_atom_mi355x_multi",
+    "runtime": {
+      "name": "docker",
+      "args": {
+        "network": "host",
+        "ipc": "host",
+        "privileged": true,
+        "shm_size": "128G"
+      }
+    }
+  }
+}

cvs/input/cluster_file/mi355x_atom_single.json

@@ -1,5 +1,5 @@
 {
-  "_comment": "Single-node MI355X example for inferencex_atom_single (ATOM driver). Pin image to match variant config / ATOM CI run.",
+  "_comment": "Single-node MI355X example for inferencex_atom (ATOM driver). Pin image to match variant config / ATOM CI run.",
   "orchestrator": "container",
   "username": "{user-id}",
   "priv_key_file": "/home/{user-id}/.ssh/id_rsa",