43df2cb2fc
### 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>
25 lines
821 B
Python
25 lines
821 B
Python
import pytest
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
from tests.e2e.singlecard.test_ilama_lora import EXPECTED_LORA_OUTPUT, MODEL_PATH, do_sample
|
|
|
|
|
|
@pytest.mark.parametrize("distributed_executor_backend", ["mp"])
|
|
def test_ilama_lora_tp2(distributed_executor_backend, ilama_lora_files):
|
|
with VllmRunner(
|
|
MODEL_PATH,
|
|
enable_lora=True,
|
|
max_loras=4,
|
|
dtype="half",
|
|
max_model_len=1024,
|
|
max_num_seqs=16,
|
|
tensor_parallel_size=2,
|
|
cudagraph_capture_sizes=[1, 2, 4, 8],
|
|
distributed_executor_backend=distributed_executor_backend,
|
|
enforce_eager=True,
|
|
) as vllm_model:
|
|
output = do_sample(vllm_model.model, ilama_lora_files, lora_id=2)
|
|
|
|
for i in range(len(EXPECTED_LORA_OUTPUT)):
|
|
assert output[i] == EXPECTED_LORA_OUTPUT[i]
|