EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Doc] Upgrade outdated doc (#4957)

Browse Source 
### What this PR does / why we need it?
Updated some issues that caused sleep mode document content to be
unavailable due to changes/outdated environment variables.

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-12-12 15:38:29 +08:00
committed by GitHub
parent 62a9fea7af
commit 4ae7588c52
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/user_guide/feature_guide/sleep_mode.md
View File

@@ -36,11 +36,12 @@ The following is a simple example of how to use sleep mode.
import torch import torch
from vllm import LLM, SamplingParams from vllm import LLM, SamplingParams
from vllm.utils import GiB_bytes from vllm.utils.mem_constants import GiB_bytes
os.environ["VLLM_USE_MODELSCOPE"] = "True" os.environ["VLLM_USE_MODELSCOPE"] = "True"
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn" os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
os.environ["VLLM_ASCEND_ENABLE_NZ"] = "0"
if __name__ == "__main__": if __name__ == "__main__":
prompt = "How are you?" prompt = "How are you?"
@@ -77,6 +78,7 @@ The following is a simple example of how to use sleep mode.
export VLLM_SERVER_DEV_MODE="1" export VLLM_SERVER_DEV_MODE="1"
export VLLM_WORKER_MULTIPROC_METHOD="spawn" export VLLM_WORKER_MULTIPROC_METHOD="spawn"
export VLLM_USE_MODELSCOPE="True" export VLLM_USE_MODELSCOPE="True"
export VLLM_ASCEND_ENABLE_NZ="0"
vllm serve Qwen/Qwen2.5-0.5B-Instruct --enable-sleep-mode vllm serve Qwen/Qwen2.5-0.5B-Instruct --enable-sleep-mode