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

11
tests/e2e/singlecard/test_cpu_offloading.py
View File

@@ -107,15 +107,13 @@ def _latency_test(llm: LLM, subscriber: MockSubscriber):
def _accuracy_test(llm: LLM, subscriber: MockSubscriber):
sampling_params = SamplingParams(max_tokens=1)
cpu_block_size = (llm.llm_engine.vllm_config.kv_transfer_config.
kv_connector_extra_config["block_size"])
cpu_block_size = llm.llm_engine.vllm_config.kv_transfer_config.kv_connector_extra_config["block_size"]
subscriber.get_new_cpu_stored_events()
# prepend prompt to be cpu block aligned
prompt = "Let's count to 10. One, two, three, four,"
while (len(llm.generate(prompt, use_tqdm=False)[0].prompt_token_ids) %
cpu_block_size != 0):
while len(llm.generate(prompt, use_tqdm=False)[0].prompt_token_ids) % cpu_block_size != 0:
prompt = ". " + prompt
assert subscriber.get_new_cpu_stored_events()
@@ -123,8 +121,7 @@ def _accuracy_test(llm: LLM, subscriber: MockSubscriber):
test_count = 100
success_count = 0
for i in range(test_count):
if (llm.generate(prompt, sampling_params,
use_tqdm=False)[0].outputs[0].text == " five"):
if llm.generate(prompt, sampling_params, use_tqdm=False)[0].outputs[0].text == " five":
success_count += 1
assert success_count >= 0.5 * test_count
@@ -143,7 +140,7 @@ def test_cpu_offloading() -> None:
"num_cpu_blocks": 1000,
"block_size": 128,
"spec_name": "NPUOffloadingSpec",
"spec_module_path": "vllm_ascend.kv_offload.npu"
"spec_module_path": "vllm_ascend.kv_offload.npu",
},
)