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

52
tests/e2e/multicard/2-cards/test_external_launcher.py
View File

@@ -29,6 +29,7 @@ from unittest.mock import patch
import pytest
import torch_npu
from modelscope import snapshot_download # type: ignore
from tests.e2e.conftest import wait_until_npu_memory_free
MODELS = ["Qwen/Qwen3-0.6B"]
@@ -39,9 +40,7 @@ DEVICE_NAME = torch_npu.npu.get_device_name(0)[:10]
@pytest.mark.parametrize("model", MODELS)
@patch.dict(os.environ, {"HCCL_BUFFSIZE": "500"})
def test_qwen3_external_launcher(model):
script = Path(
__file__
).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
script = Path(__file__).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
env = os.environ.copy()
# TODO: Change to 2 when ci machine has 4 cards
cmd = [
@@ -68,7 +67,7 @@ def test_qwen3_external_launcher(model):
stderr=subprocess.STDOUT,
timeout=600,
)
output = proc.stdout.decode(errors='ignore')
output = proc.stdout.decode(errors="ignore")
print(output)
@@ -81,16 +80,24 @@ def test_qwen3_external_launcher(model):
@pytest.mark.parametrize("model", MOE_MODELS)
@wait_until_npu_memory_free()
def test_qwen3_moe_external_launcher_ep_tp2(model):
script = Path(
__file__
).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
script = Path(__file__).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
env = os.environ.copy()
# TODO: Change to 2 when ci machine has 4 cards
cmd = [
sys.executable,
str(script), "--model", model, "--tp-size", "2", "--node-size", "1",
"--node-rank", "0", "--proc-per-node", "2", "--trust-remote-code",
"--enable-expert-parallel"
str(script),
"--model",
model,
"--tp-size",
"2",
"--node-size",
"1",
"--node-rank",
"0",
"--proc-per-node",
"2",
"--trust-remote-code",
"--enable-expert-parallel",
]
print(f"Running subprocess: {' '.join(cmd)}")
@@ -101,7 +108,7 @@ def test_qwen3_moe_external_launcher_ep_tp2(model):
stderr=subprocess.STDOUT,
timeout=600,
)
output = proc.stdout.decode(errors='ignore')
output = proc.stdout.decode(errors="ignore")
print(output)
@@ -113,9 +120,7 @@ def test_qwen3_moe_external_launcher_ep_tp2(model):
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_NZ": "0"})
@wait_until_npu_memory_free()
def test_qwen3_external_launcher_with_sleepmode():
script = Path(
__file__
).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
script = Path(__file__).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
env = os.environ.copy()
# TODO: Change to 2 when ci machine has 4 cards
cmd = [
@@ -147,7 +152,7 @@ def test_qwen3_external_launcher_with_sleepmode():
stderr=subprocess.STDOUT,
timeout=300,
)
output = proc.stdout.decode(errors='ignore')
output = proc.stdout.decode(errors="ignore")
print(output)
@@ -158,9 +163,7 @@ def test_qwen3_external_launcher_with_sleepmode():
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_NZ": "0"})
def test_qwen3_external_launcher_with_sleepmode_level2():
script = Path(
__file__
).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
script = Path(__file__).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
env = os.environ.copy()
model_path = snapshot_download("Qwen/Qwen3-8B")
# TODO: Add moe model test
@@ -195,7 +198,7 @@ def test_qwen3_external_launcher_with_sleepmode_level2():
stderr=subprocess.STDOUT,
timeout=300,
)
output = proc.stdout.decode(errors='ignore')
output = proc.stdout.decode(errors="ignore")
print(output)
@@ -210,14 +213,9 @@ def test_qwen3_external_launcher_with_sleepmode_level2():
)
@pytest.mark.parametrize("model", MODELS)
@wait_until_npu_memory_free()
@patch.dict(os.environ, {
"VLLM_ASCEND_ENABLE_MATMUL_ALLREDUCE": "1",
"HCCL_BUFFSIZE": "500"
})
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_MATMUL_ALLREDUCE": "1", "HCCL_BUFFSIZE": "500"})
def test_qwen3_external_launcher_with_matmul_allreduce(model):
script = Path(
__file__
).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
script = Path(__file__).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
env = os.environ.copy()
cmd = [
sys.executable,
@@ -236,7 +234,7 @@ def test_qwen3_external_launcher_with_matmul_allreduce(model):
timeout=600,
)
output = proc.stdout.decode(errors='ignore')
output = proc.stdout.decode(errors="ignore")
print(output)
assert "Generated text:" in output