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

[Lint]Style: Convert test/ to ruff format(Batch #5) (#6747)

Browse Source 
### What this PR does / why we need it?
| File Path |
| :--- |
| `tests/e2e/singlecard/compile/backend.py` |
| `tests/e2e/singlecard/compile/test_graphex_norm_quant_fusion.py` |
| `tests/e2e/singlecard/compile/test_graphex_qknorm_rope_fusion.py` |
| `tests/e2e/singlecard/compile/test_norm_quant_fusion.py` |
| `tests/e2e/singlecard/model_runner_v2/test_basic.py` |
| `tests/e2e/singlecard/test_aclgraph_accuracy.py` |
| `tests/e2e/singlecard/test_aclgraph_batch_invariant.py` |
| `tests/e2e/singlecard/test_aclgraph_mem.py` |
| `tests/e2e/singlecard/test_async_scheduling.py` |
| `tests/e2e/singlecard/test_auto_fit_max_mode_len.py` |
| `tests/e2e/singlecard/test_batch_invariant.py` |
| `tests/e2e/singlecard/test_camem.py` |
| `tests/e2e/singlecard/test_completion_with_prompt_embeds.py` |
| `tests/e2e/singlecard/test_cpu_offloading.py` |
| `tests/e2e/singlecard/test_guided_decoding.py` |
| `tests/e2e/singlecard/test_ilama_lora.py` |
| `tests/e2e/singlecard/test_llama32_lora.py` |
| `tests/e2e/singlecard/test_models.py` |
| `tests/e2e/singlecard/test_multistream_overlap_shared_expert.py` |
| `tests/e2e/singlecard/test_quantization.py` |
| `tests/e2e/singlecard/test_qwen3_multi_loras.py` |
| `tests/e2e/singlecard/test_sampler.py` |
| `tests/e2e/singlecard/test_vlm.py` |
| `tests/e2e/singlecard/test_xlite.py` |
| `tests/e2e/singlecard/utils.py` |

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

### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main:
9562912cea

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
This commit is contained in:
SILONG ZENG
2026-02-24 15:50:00 +08:00
committed by GitHub
parent 747484cb64
commit 62ea664aa7
26 changed files with 859 additions and 1052 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
tests/e2e/singlecard/test_sampler.py
View File

@@ -25,15 +25,11 @@ def test_qwen3_topk() -> None:
example_prompts = [
"Hello, my name is",
]
sampling_params = SamplingParams(max_tokens=5,
temperature=0.0,
top_k=50,
top_p=0.9)
sampling_params = SamplingParams(max_tokens=5, temperature=0.0, top_k=50, top_p=0.9)
with VllmRunner("Qwen/Qwen3-0.6B",
max_model_len=8192,
cudagraph_capture_sizes=[1, 2, 4, 8],
gpu_memory_utilization=0.7) as runner:
with VllmRunner(
"Qwen/Qwen3-0.6B", max_model_len=8192, cudagraph_capture_sizes=[1, 2, 4, 8], gpu_memory_utilization=0.7
) as runner:
runner.generate(example_prompts, sampling_params)
@@ -42,29 +38,25 @@ def test_qwen3_prompt_logprobs() -> None:
"Hello, my name is",
]
with VllmRunner("Qwen/Qwen3-0.6B",
max_model_len=8192,
cudagraph_capture_sizes=[1, 2, 4, 8],
gpu_memory_utilization=0.7) as runner:
runner.generate_greedy_logprobs(example_prompts,
max_tokens=5,
num_logprobs=1)
with VllmRunner(
"Qwen/Qwen3-0.6B", max_model_len=8192, cudagraph_capture_sizes=[1, 2, 4, 8], gpu_memory_utilization=0.7
) as runner:
runner.generate_greedy_logprobs(example_prompts, max_tokens=5, num_logprobs=1)
def test_qwen3_exponential_overlap() -> None:
example_prompts = [
"Hello, my name is",
]
sampling_params = SamplingParams(max_tokens=5,
temperature=1.0,
top_k=50,
top_p=0.9)
sampling_params = SamplingParams(max_tokens=5, temperature=1.0, top_k=50, top_p=0.9)
with VllmRunner("Qwen/Qwen3-0.6B",
max_model_len=8192,
cudagraph_capture_sizes=[1, 2, 4, 8],
gpu_memory_utilization=0.7,
additional_config={
"enable_async_exponential": True,
}) as runner:
with VllmRunner(
"Qwen/Qwen3-0.6B",
max_model_len=8192,
cudagraph_capture_sizes=[1, 2, 4, 8],
gpu_memory_utilization=0.7,
additional_config={
"enable_async_exponential": True,
},
) as runner:
runner.generate(example_prompts, sampling_params)