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

Fix typo of VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE (#1112)

Browse Source 
### What this PR does / why we need it?
Fix typo of VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE

### Does this PR introduce _any_ user-facing change?

No

### How was this patch tested?

CI passed

Signed-off-by: linfeng-yuan <1102311262@qq.com>
This commit is contained in:
linfeng-yuan
2025-06-07 19:45:33 +08:00
committed by GitHub
parent 20dedba5d1
commit b80a484864
4 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/multicard/test_offline_inference_distributed.py
View File

@@ -61,7 +61,7 @@ def test_models_distributed_DeepSeek():
vllm_model.generate_greedy(example_prompts, max_tokens)
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_TOPK_OPTIMZE": "1"})
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE": "1"})
def test_models_distributed_topk() -> None:
example_prompts = [
"vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.",

2
tests/singlecard/test_offline_inference.py
View File

@@ -83,7 +83,7 @@ def test_multimodal(model, prompt_template, vllm_runner):
max_tokens=64)
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_TOPK_OPTIMZE": "1"})
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE": "1"})
def test_models_topk() -> None:
example_prompts = [
"Hello, my name is",