CI problems

chenxi-hh · chenxi-hh · commit 2f24a00758e3 · 2025-11-26T15:21:18.000+08:00
Signed-off-by: chenxi-hh &lt;chen464822955@163.com&gt;
diff --git a/tests/e2e/multicard/test_quantization.py b/tests/e2e/multicard/test_quantization.py
@@ -27,7 +27,7 @@
 
 def test_models_distributed_quantized_W8A8():
     example_prompts = [
-        "Hello, my name is",
+        "The president of the United States is",
     ]
     max_tokens = 5
     with VllmRunner(snapshot_download("neuralmagic/Qwen2.5-3B-quantized.w8a8"),
@@ -38,7 +38,7 @@ def test_models_distributed_quantized_W8A8():
         vllm_output = vllm_model.generate_greedy(example_prompts, max_tokens)
 
     golden_results = [
-        'Hello, my name is the head of state and',
+        'The president of the United States is the head of state and',
     ]
 
     for i in range(len(vllm_output)):

Original file line number	Diff line number	Diff line change
`@@ -27,7 +27,7 @@`
`27`	`27`
`28`	`28`	`def test_models_distributed_quantized_W8A8():`
`29`	`29`	`example_prompts = [`
`30`		`- "Hello, my name is",`
	`30`	`+ "The president of the United States is",`
`31`	`31`	`]`
`32`	`32`	`max_tokens = 5`
`33`	`33`	`with VllmRunner(snapshot_download("neuralmagic/Qwen2.5-3B-quantized.w8a8"),`
`@@ -38,7 +38,7 @@ def test_models_distributed_quantized_W8A8():`
`38`	`38`	`vllm_output = vllm_model.generate_greedy(example_prompts, max_tokens)`
`39`	`39`
`40`	`40`	`golden_results = [`
`41`		`- 'Hello, my name is the head of state and',`
	`41`	`+ 'The president of the United States is the head of state and',`
`42`	`42`	`]`
`43`	`43`
`44`	`44`	`for i in range(len(vllm_output)):`