[Examples][last/6] Resettle examples. (#41084)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-05-07 19:42:12 -07:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 57c2f724c1
commit 1d694e78c9
61 changed files with 60 additions and 88 deletions
+2 -2
View File
@@ -40,7 +40,7 @@ Deploy the following yaml file `lws.yaml`
command:
- sh
- -c
- "bash /vllm-workspace/examples/online_serving/multi-node-serving.sh leader --ray_cluster_size=$(LWS_GROUP_SIZE);
- "bash /vllm-workspace/examples/ray_serving/multi-node-serving.sh leader --ray_cluster_size=$(LWS_GROUP_SIZE);
vllm serve meta-llama/Meta-Llama-3.1-405B-Instruct --port 8080 --tensor-parallel-size 8 --pipeline_parallel_size 2"
resources:
limits:
@@ -73,7 +73,7 @@ Deploy the following yaml file `lws.yaml`
command:
- sh
- -c
- "bash /vllm-workspace/examples/online_serving/multi-node-serving.sh worker --ray_address=$(LWS_LEADER_ADDRESS)"
- "bash /vllm-workspace/examples/ray_serving/multi-node-serving.sh worker --ray_address=$(LWS_LEADER_ADDRESS)"
resources:
limits:
nvidia.com/gpu: "8"