[typo] fix typo of VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE

Signed-off-by: linfeng-yuan <1102311262@qq.com>

Author: linfeng-yuan

tests/multicard/test_offline_inference_distributed.py

@@ -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.",

tests/singlecard/test_offline_inference.py

@@ -85,7 +85,7 @@ 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",

vllm_ascend/envs.py

@@ -57,8 +57,8 @@
     lambda: bool(int(os.getenv("VLLM_ENABLE_MC2", '0'))),
     # Whether to enable the topk optimization. It's disabled by default for experimental support
     # We'll make it enabled by default in the future.
-    "VLLM_ASCEND_ENABLE_TOPK_OPTIMZE":
-    lambda: bool(int(os.getenv("VLLM_ASCEND_ENABLE_TOPK_OPTIMZE", '0'))),
+    "VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE":
+    lambda: bool(int(os.getenv("VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE", '0'))),
     # Whether to use LCCL communication. If not set, the default value is False.
     "USING_LCCL_COM":
     lambda: bool(int(os.getenv("USING_LCCL_COM", '0'))),

vllm_ascend/patch/worker/patch_common/patch_sampler.py

@@ -97,5 +97,5 @@ def topk_topp_forward_native(
 
 
 Sampler.apply_min_p = apply_min_p
-if envs.VLLM_ASCEND_ENABLE_TOPK_OPTIMZE:
+if envs.VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE:
     TopKTopPSampler.forward_native = topk_topp_forward_native