Skip to content

Commit 90d2310

Browse files
authored
fix: no need to manually load the nvidia drivers after reboot (#47)
1 parent 9f86317 commit 90d2310

2 files changed

Lines changed: 14 additions & 16 deletions

File tree

application/service/akash_cluster_service.py

Lines changed: 14 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -181,20 +181,20 @@ def _create_k3s_tasks(self, nodes):
181181
)
182182
)
183183

184-
# for i, node in reversed(list(enumerate(nodes))):
185-
# if node.install_gpu_drivers:
186-
# node_type = "main_node" if i == 0 else "worker_node"
187-
# k3s_tasks.append(
188-
# Task(
189-
# str(uuid4()),
190-
# f"restart_node_{node.hostname}",
191-
# f"Restart node {node.hostname}",
192-
# self.k3s_service._reboot_node,
193-
# ssh_client,
194-
# node,
195-
# node_type,
196-
# )
197-
# )
184+
for i, node in reversed(list(enumerate(nodes))):
185+
if node.install_gpu_drivers:
186+
node_type = "main_node" if i == 0 else "worker_node"
187+
k3s_tasks.append(
188+
Task(
189+
str(uuid4()),
190+
f"restart_node_{node.hostname}",
191+
f"Restart node {node.hostname}",
192+
self.k3s_service._reboot_node,
193+
ssh_client,
194+
node,
195+
node_type,
196+
)
197+
)
198198

199199
return k3s_tasks
200200

application/service/k3s_service.py

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -594,8 +594,6 @@ def _install_nvidia_drivers(
594594
"apt update",
595595
"apt-get install build-essential dkms linux-headers-$(uname -r) -y",
596596
"apt-get install nvidia-driver-570 -y",
597-
"modprobe nvidia",
598-
"nvidia-smi"
599597
]
600598

601599
nvidia_5090_commands = [

0 commit comments

Comments
 (0)