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

[lint]clean code (#5218)

Browse Source 
### What this PR does / why we need it?
Fix lint error inreoduced by
https://github.com/vllm-project/vllm-ascend/pull/5141

- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
This commit is contained in:
weiguihua2
2025-12-20 18:24:04 +08:00
committed by GitHub
parent bbde0f9743
commit 21745221a3
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tests/e2e/multicard/long_sequence/test_accuracy.py
View File

@@ -81,17 +81,17 @@ def test_output_between_tp_and_cp(
} }
cp_full_kwargs = {} cp_full_kwargs = {}
cp_full_kwargs.update(common_kwargs) cp_full_kwargs.update(common_kwargs) # type: ignore
cp_full_kwargs.update(cp_kwargs) cp_full_kwargs.update(cp_kwargs) # type: ignore
tp_full_kwargs = {} tp_full_kwargs = {}
tp_full_kwargs.update(common_kwargs) tp_full_kwargs.update(common_kwargs) # type: ignore
tp_full_kwargs.update(tp_kwargs) tp_full_kwargs.update(tp_kwargs) # type: ignore
with VllmRunner(model, **cp_full_kwargs) as runner: with VllmRunner(model, **cp_full_kwargs) as runner: # type: ignore
vllm_context_parallel_outputs = runner.generate_greedy( vllm_context_parallel_outputs = runner.generate_greedy(
prompts, max_tokens) prompts, max_tokens)
with VllmRunner(model, **tp_full_kwargs) as runner: with VllmRunner(model, **tp_full_kwargs) as runner: # type: ignore
vllm_eager_outputs = runner.generate_greedy(prompts, max_tokens) vllm_eager_outputs = runner.generate_greedy(prompts, max_tokens)
check_outputs_equal( check_outputs_equal(