### 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:
@@ -27,6 +27,7 @@ MODELS = [
|
||||
SHARED_STORAGE_PATH = "/dev/shm/epd/storage"
|
||||
TENSOR_PARALLELS = [1]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize("model", MODELS)
|
||||
@pytest.mark.parametrize("tp_size", TENSOR_PARALLELS)
|
||||
@@ -36,36 +37,61 @@ async def test_models(model: str, tp_size: int) -> None:
|
||||
vllm_server_args = [
|
||||
[
|
||||
"--port",
|
||||
str(encode_port), "--model", model, "--gpu-memory-utilization",
|
||||
"0.01", "--tensor-parallel-size",
|
||||
str(tp_size), "--enforce-eager", "--no-enable-prefix-caching",
|
||||
"--max-model-len", "10000", "--max-num-batched-tokens", "10000",
|
||||
"--max-num-seqs", "1", "--ec-transfer-config",
|
||||
'{"ec_connector_extra_config":{"shared_storage_path":"' +
|
||||
SHARED_STORAGE_PATH +
|
||||
'"},"ec_connector":"ECExampleConnector","ec_role": "ec_producer"}'
|
||||
str(encode_port),
|
||||
"--model",
|
||||
model,
|
||||
"--gpu-memory-utilization",
|
||||
"0.01",
|
||||
"--tensor-parallel-size",
|
||||
str(tp_size),
|
||||
"--enforce-eager",
|
||||
"--no-enable-prefix-caching",
|
||||
"--max-model-len",
|
||||
"10000",
|
||||
"--max-num-batched-tokens",
|
||||
"10000",
|
||||
"--max-num-seqs",
|
||||
"1",
|
||||
"--ec-transfer-config",
|
||||
'{"ec_connector_extra_config":{"shared_storage_path":"'
|
||||
+ SHARED_STORAGE_PATH
|
||||
+ '"},"ec_connector":"ECExampleConnector","ec_role": "ec_producer"}',
|
||||
],
|
||||
[
|
||||
"--port",
|
||||
str(pd_port), "--model", model, "--gpu-memory-utilization", "0.95",
|
||||
str(pd_port),
|
||||
"--model",
|
||||
model,
|
||||
"--gpu-memory-utilization",
|
||||
"0.95",
|
||||
"--tensor-parallel-size",
|
||||
str(tp_size), "--enforce-eager", "--max-model-len", "10000",
|
||||
"--max-num-batched-tokens", "10000", "--max-num-seqs", "128",
|
||||
str(tp_size),
|
||||
"--enforce-eager",
|
||||
"--max-model-len",
|
||||
"10000",
|
||||
"--max-num-batched-tokens",
|
||||
"10000",
|
||||
"--max-num-seqs",
|
||||
"128",
|
||||
"--ec-transfer-config",
|
||||
'{"ec_connector_extra_config":{"shared_storage_path":"' +
|
||||
SHARED_STORAGE_PATH +
|
||||
'"},"ec_connector":"ECExampleConnector","ec_role": "ec_consumer"}'
|
||||
]
|
||||
'{"ec_connector_extra_config":{"shared_storage_path":"'
|
||||
+ SHARED_STORAGE_PATH
|
||||
+ '"},"ec_connector":"ECExampleConnector","ec_role": "ec_consumer"}',
|
||||
],
|
||||
]
|
||||
proxy_port = get_open_port()
|
||||
proxy_args = [
|
||||
"--host", "127.0.0.1", "--port",
|
||||
str(proxy_port), "--encode-servers-urls",
|
||||
f"http://localhost:{encode_port}", "--decode-servers-urls",
|
||||
f"http://localhost:{pd_port}", "--prefill-servers-urls", "disable"
|
||||
"--host",
|
||||
"127.0.0.1",
|
||||
"--port",
|
||||
str(proxy_port),
|
||||
"--encode-servers-urls",
|
||||
f"http://localhost:{encode_port}",
|
||||
"--decode-servers-urls",
|
||||
f"http://localhost:{pd_port}",
|
||||
"--prefill-servers-urls",
|
||||
"disable",
|
||||
]
|
||||
|
||||
with RemoteEPDServer(vllm_serve_args=vllm_server_args) as _:
|
||||
with DisaggEpdProxy(proxy_args=proxy_args) as proxy:
|
||||
send_image_request(model, proxy)
|
||||
|
||||
with RemoteEPDServer(vllm_serve_args=vllm_server_args) as _, DisaggEpdProxy(proxy_args=proxy_args) as proxy:
|
||||
send_image_request(model, proxy)
|
||||
|
||||
Reference in New Issue
Block a user