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

79
tests/e2e/multicard/2-cards/test_qwen3_moe.py
View File

@@ -34,11 +34,11 @@ def test_qwen3_moe_distributed_mp_tp2_ep():
]
max_tokens = 5
with VllmRunner(
"Qwen/Qwen3-30B-A3B",
tensor_parallel_size=2,
enable_expert_parallel=True,
cudagraph_capture_sizes=[1, 2, 4, 8],
distributed_executor_backend="mp",
"Qwen/Qwen3-30B-A3B",
tensor_parallel_size=2,
enable_expert_parallel=True,
cudagraph_capture_sizes=[1, 2, 4, 8],
distributed_executor_backend="mp",
) as vllm_model:
vllm_model.generate_greedy(example_prompts, max_tokens)
@@ -49,27 +49,27 @@ def test_qwen3_moe_w8a8_distributed_tp2():
]
max_tokens = 5
with VllmRunner(
"vllm-ascend/Qwen3-30B-A3B-W8A8",
max_model_len=8192,
tensor_parallel_size=2,
cudagraph_capture_sizes=[1, 2, 4, 8],
quantization="ascend",
"vllm-ascend/Qwen3-30B-A3B-W8A8",
max_model_len=8192,
tensor_parallel_size=2,
cudagraph_capture_sizes=[1, 2, 4, 8],
quantization="ascend",
) as vllm_model:
vllm_model.generate_greedy(example_prompts, max_tokens)
def test_qwen3_moe_distributed_aiv_tp2():
os.environ['HCCL_OP_EXPANSION_MODE'] = 'AIV'
os.environ["HCCL_OP_EXPANSION_MODE"] = "AIV"
example_prompts = [
"Hello, my name is",
]
dtype = "auto"
max_tokens = 5
with VllmRunner(
"Qwen/Qwen3-30B-A3B",
dtype=dtype,
tensor_parallel_size=2,
cudagraph_capture_sizes=[1, 2, 4, 8],
"Qwen/Qwen3-30B-A3B",
dtype=dtype,
tensor_parallel_size=2,
cudagraph_capture_sizes=[1, 2, 4, 8],
) as vllm_model:
vllm_model.generate_greedy(example_prompts, max_tokens)
@@ -80,23 +80,24 @@ async def test_qwen3_moe_w8a8_distributed_tp2_ep_dynamic_eplb():
port = get_open_port()
compilation_config = json.dumps({"cudagraph_capture_sizes": [8]})
server_args = [
"--max_model_len", "8192", "--tensor_parallel_size", "2",
"--enable_expert_parallel", "--quantization", "ascend", "--port",
str(port), "--compilation-config", compilation_config
"--max_model_len",
"8192",
"--tensor_parallel_size",
"2",
"--enable_expert_parallel",
"--quantization",
"ascend",
"--port",
str(port),
"--compilation-config",
compilation_config,
]
env_dict = {"HCCL_BUFFSIZE": "1024"}
with RemoteOpenAIServer(model,
server_args,
server_port=port,
auto_port=False,
env_dict=env_dict) as server:
with RemoteOpenAIServer(model, server_args, server_port=port, auto_port=False, env_dict=env_dict) as server:
client = server.get_async_client()
batch = await client.completions.create(model=model,
prompt="What is deeplearning?",
max_tokens=400,
temperature=0,
top_p=1.0,
n=1)
batch = await client.completions.create(
model=model, prompt="What is deeplearning?", max_tokens=400, temperature=0, top_p=1.0, n=1
)
gt_choices: list[openai.types.CompletionChoice] = batch.choices
# dynamic eplb test
@@ -108,22 +109,14 @@ async def test_qwen3_moe_w8a8_distributed_tp2_ep_dynamic_eplb():
"dynamic_eplb": True,
"expert_heat_collection_interval": 100,
"algorithm_execution_interval": 20,
"num_redundant_experts": 2
"num_redundant_experts": 2,
}
}
server_args.extend(["--additional-config", json.dumps(additional_config)])
with RemoteOpenAIServer(model,
server_args,
server_port=port,
auto_port=False,
env_dict=env_dict) as server:
with RemoteOpenAIServer(model, server_args, server_port=port, auto_port=False, env_dict=env_dict) as server:
client = server.get_async_client()
batch = await client.completions.create(model=model,
prompt="What is deeplearning?",
max_tokens=400,
temperature=0,
top_p=1.0,
n=1)
batch = await client.completions.create(
model=model, prompt="What is deeplearning?", max_tokens=400, temperature=0, top_p=1.0, n=1
)
eplb_choices: list[openai.types.CompletionChoice] = batch.choices
assert gt_choices[0].text == eplb_choices[
0].text, f"{gt_choices[0].text=} \n {eplb_choices[0].text=}"
assert gt_choices[0].text == eplb_choices[0].text, f"{gt_choices[0].text=} \n {eplb_choices[0].text=}"