3cf059a72b
### What this PR does / why we need it?
Upgrade vllm commit to 0105 (8be6432bdaf6275664d857b1e5e9bf8ed1ce299e)
1. Remove `maybe_padded_num_tokens` arg in `model_runner_v1.py` since
https://github.com/vllm-project/vllm/pull/31517 deleted unused arg
2. Remove dense `Qwen/Qwen3-0.6B` in
`tests/e2e/multicard/test_aclgraph_capture_replay.py` and
`tests/e2e/multicard/test_data_parallel.py` due to
https://github.com/vllm-project/vllm/pull/30739
where offline data parallel mode will not be supported/useful for dense
models
3. Adapt `vllm_ascend/worker/worker.py` due to
https://github.com/vllm-project/vllm/pull/31584
4. Adapt `self.block_size` calling due to
https://github.com/vllm-project/vllm/pull/31540
5. Modify `test_mla_v1.py` due to
https://github.com/vllm-project/vllm/pull/28454 , which refactorred
`get_head_size()`
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
7157596103
Signed-off-by: wjunLu <wjunlu217@gmail.com>
53 lines
1.2 KiB
Python
53 lines
1.2 KiB
Python
"""
|
|
Run `pytest tests/e2e/multicard/test_data_parallel_tp2.py`.
|
|
"""
|
|
|
|
import os
|
|
import subprocess
|
|
import sys
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
MODELS = ["Qwen/Qwen3-30B-A3B"]
|
|
|
|
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@pytest.mark.parametrize("max_tokens", [32])
|
|
@patch.dict(os.environ, {"ASCEND_RT_VISIBLE_DEVICES": "0,1,2,3"})
|
|
def test_qwen3_inference_dp2_tp2(model, max_tokens):
|
|
script = "examples/offline_data_parallel.py"
|
|
|
|
env = os.environ.copy()
|
|
|
|
cmd = [
|
|
sys.executable,
|
|
script,
|
|
"--model",
|
|
model,
|
|
"--dp-size",
|
|
"2",
|
|
"--tp-size",
|
|
"2",
|
|
"--node-size",
|
|
"1",
|
|
"--node-rank",
|
|
"0",
|
|
"--trust-remote-code",
|
|
]
|
|
|
|
print(f"Running subprocess: {' '.join(cmd)}")
|
|
proc = subprocess.run(cmd,
|
|
env=env,
|
|
stdout=subprocess.PIPE,
|
|
stderr=subprocess.STDOUT,
|
|
timeout=600)
|
|
output = proc.stdout.decode(errors='ignore')
|
|
|
|
print(output)
|
|
|
|
assert "DP rank 0 needs to process" in output
|
|
assert "DP rank 1 needs to process" in output
|
|
assert "Generated text:" in output
|
|
assert proc.returncode == 0
|