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

[Lint]Style: Convert example to ruff format (#5863)

Browse Source 
### What this PR does / why we need it?
This PR fixes linting issues in the `example/` to align with the
project's Ruff configuration.

- vLLM version: v0.13.0
- vLLM main:
bde38c11df

Signed-off-by: root <root@LAPTOP-VQKDDVMG.localdomain>
Co-authored-by: root <root@LAPTOP-VQKDDVMG.localdomain>
This commit is contained in:
SILONG ZENG
2026-01-13 20:46:50 +08:00
committed by GitHub
parent f7b904641e
commit 78d5ce3e01
23 changed files with 678 additions and 1037 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/offline_inference_sleep_mode_npu.py
View File

@@ -25,11 +25,12 @@ from vllm.utils.mem_constants import GiB_bytes
os.environ["VLLM_USE_MODELSCOPE"] = "True"
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
def main():
prompt = "How are you?"
free, total = torch.npu.mem_get_info()
print(f"Free memory before sleep: {free / 1024 ** 3:.2f} GiB")
print(f"Free memory before sleep: {free / 1024**3:.2f} GiB")
# record npu memory use baseline in case other process is running
used_bytes_baseline = total - free
llm = LLM("Qwen/Qwen2.5-0.5B-Instruct", enable_sleep_mode=True)
@@ -39,9 +40,7 @@ def main():
llm.sleep(level=1)
free_npu_bytes_after_sleep, total = torch.npu.mem_get_info()
print(
f"Free memory after sleep: {free_npu_bytes_after_sleep / 1024 ** 3:.2f} GiB"
)
print(f"Free memory after sleep: {free_npu_bytes_after_sleep / 1024**3:.2f} GiB")
used_bytes = total - free_npu_bytes_after_sleep - used_bytes_baseline
# now the memory usage should be less than the model weights
# (0.5B model, 1GiB weights)