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

[Lint]Style: Convert test/ to ruff format(Batch #1) (#6738)

Browse Source 
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
| `tests/e2e/310p/multicard/test_vl_model_multicard.py` |
| `tests/e2e/310p/singlecard/test_vl_model_singlecard.py` |
| `tests/e2e/310p/test_utils.py` |
| `tests/e2e/conftest.py` |
| `tests/e2e/model_utils.py` |
| `tests/e2e/models/conftest.py` |
| `tests/e2e/models/test_lm_eval_correctness.py` |
| `tests/e2e/multicard/2-cards/spec_decode/test_spec_decode.py` |
| `tests/e2e/multicard/2-cards/test_aclgraph_capture_replay.py` |
| `tests/e2e/multicard/2-cards/test_data_parallel.py` |
| `tests/e2e/multicard/2-cards/test_disaggregated_encoder.py` |
| `tests/e2e/multicard/2-cards/test_expert_parallel.py` |
| `tests/e2e/multicard/2-cards/test_external_launcher.py` |
| `tests/e2e/multicard/2-cards/test_full_graph_mode.py` |
| `tests/e2e/multicard/2-cards/test_ilama_lora_tp2.py` |
| `tests/e2e/multicard/2-cards/test_offline_inference_distributed.py` |
| `tests/e2e/multicard/2-cards/test_offline_weight_load.py` |
| `tests/e2e/multicard/2-cards/test_pipeline_parallel.py` |
| `tests/e2e/multicard/2-cards/test_prefix_caching.py` |
| `tests/e2e/multicard/2-cards/test_quantization.py` |
| `tests/e2e/multicard/2-cards/test_qwen3_moe.py` |
| `tests/e2e/multicard/2-cards/test_qwen3_moe_routing_replay.py` |
| `tests/e2e/multicard/2-cards/test_qwen3_performance.py` |
| `tests/e2e/multicard/2-cards/test_shared_expert_dp.py` |
| `tests/e2e/multicard/2-cards/test_single_request_aclgraph.py` |
| `tests/e2e/multicard/2-cards/test_sp_pass.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>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
SILONG ZENG
2026-03-10 09:52:50 +08:00
committed by GitHub
parent 9216e1b050
commit 43df2cb2fc
27 changed files with 753 additions and 859 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/e2e/models/conftest.py
View File

@@ -55,16 +55,12 @@ def report_dir(pytestconfig):
def pytest_generate_tests(metafunc):
if "config_filename" in metafunc.fixturenames:
if metafunc.config.getoption("--config-list-file"):
rel_path = metafunc.config.getoption("--config-list-file")
config_list_file = Path(rel_path).resolve()
config_dir = config_list_file.parent
with open(config_list_file, encoding="utf-8") as f:
configs = [
config_dir / line.strip() for line in f
if line.strip() and not line.startswith("#")
]
configs = [config_dir / line.strip() for line in f if line.strip() and not line.startswith("#")]
metafunc.parametrize("config_filename", configs)
else:
single_config = metafunc.config.getoption("--config")

77
tests/e2e/models/test_lm_eval_correctness.py
View File

@@ -24,16 +24,15 @@ class EnvConfig:
@pytest.fixture
def env_config() -> EnvConfig:
return EnvConfig(vllm_version=os.getenv('VLLM_VERSION', 'unknown'),
vllm_commit=os.getenv('VLLM_COMMIT', 'unknown'),
vllm_ascend_version=os.getenv('VLLM_ASCEND_VERSION',
'unknown'),
vllm_ascend_commit=os.getenv('VLLM_ASCEND_COMMIT',
'unknown'),
cann_version=os.getenv('CANN_VERSION', 'unknown'),
torch_version=os.getenv('TORCH_VERSION', 'unknown'),
torch_npu_version=os.getenv('TORCH_NPU_VERSION',
'unknown'))
return EnvConfig(
vllm_version=os.getenv("VLLM_VERSION", "unknown"),
vllm_commit=os.getenv("VLLM_COMMIT", "unknown"),
vllm_ascend_version=os.getenv("VLLM_ASCEND_VERSION", "unknown"),
vllm_ascend_commit=os.getenv("VLLM_ASCEND_COMMIT", "unknown"),
cann_version=os.getenv("CANN_VERSION", "unknown"),
torch_version=os.getenv("TORCH_VERSION", "unknown"),
torch_npu_version=os.getenv("TORCH_NPU_VERSION", "unknown"),
)
def build_model_args(eval_config, tp_size):
@@ -48,9 +47,13 @@ def build_model_args(eval_config, tp_size):
"max_model_len": max_model_len,
}
for s in [
"max_images", "gpu_memory_utilization", "enable_expert_parallel",
"tensor_parallel_size", "enforce_eager", "enable_thinking",
"quantization"
"max_images",
"gpu_memory_utilization",
"enable_expert_parallel",
"tensor_parallel_size",
"enforce_eager",
"enable_thinking",
"quantization",
]:
val = eval_config.get(s, None)
if val is not None:
@@ -68,7 +71,7 @@ def generate_report(tp_size, eval_config, report_data, report_dir, env_config):
model_args = build_model_args(eval_config, tp_size)
parallel_mode = f"TP{model_args.get('tensor_parallel_size', 1)}"
if model_args.get('enable_expert_parallel', False):
if model_args.get("enable_expert_parallel", False):
parallel_mode += " + EP"
execution_model = f"{'Eager' if model_args.get('enforce_eager', False) else 'ACLGraph'}"
@@ -93,17 +96,16 @@ def generate_report(tp_size, eval_config, report_data, report_dir, env_config):
num_fewshot=eval_config.get("num_fewshot", "N/A"),
rows=report_data["rows"],
parallel_mode=parallel_mode,
execution_model=execution_model)
execution_model=execution_model,
)
report_output = os.path.join(
report_dir, f"{os.path.basename(eval_config['model_name'])}.md")
report_output = os.path.join(report_dir, f"{os.path.basename(eval_config['model_name'])}.md")
os.makedirs(os.path.dirname(report_output), exist_ok=True)
with open(report_output, 'w', encoding='utf-8') as f:
with open(report_output, "w", encoding="utf-8") as f:
f.write(report_content)
def test_lm_eval_correctness_param(config_filename, tp_size, report_dir,
env_config):
def test_lm_eval_correctness_param(config_filename, tp_size, report_dir, env_config):
eval_config = yaml.safe_load(config_filename.read_text(encoding="utf-8"))
model_args = build_model_args(eval_config, tp_size)
success = True
@@ -135,25 +137,26 @@ def test_lm_eval_correctness_param(config_filename, tp_size, report_dir,
metric_name = metric["name"]
ground_truth = metric["value"]
measured_value = round(task_result[metric_name], 4)
task_success = bool(
np.isclose(ground_truth, measured_value, rtol=RTOL))
task_success = bool(np.isclose(ground_truth, measured_value, rtol=RTOL))
success = success and task_success
print(f"{task_name} | {metric_name}: "
f"ground_truth={ground_truth} | measured={measured_value} | "
f"success={'✅' if task_success else '❌'}")
print(
f"{task_name} | {metric_name}: "
f"ground_truth={ground_truth} | measured={measured_value} | "
f"success={'✅' if task_success else '❌'}"
)
report_data["rows"].append({
"task":
task_name,
"metric":
metric_name,
"value":
f"✅{measured_value}" if success else f"❌{measured_value}",
"stderr":
task_result[
metric_name.replace(',', '_stderr,') if metric_name ==
"acc,none" else metric_name.replace(',', '_stderr,')]
})
report_data["rows"].append(
{
"task": task_name,
"metric": metric_name,
"value": f"✅{measured_value}" if success else f"❌{measured_value}",
"stderr": task_result[
metric_name.replace(",", "_stderr,")
if metric_name == "acc,none"
else metric_name.replace(",", "_stderr,")
],
}
)
generate_report(tp_size, eval_config, report_data, report_dir, env_config)
assert success