[Model] Add qwen3Next support in Main (#4596)

### What this PR does / why we need it?
Add Qwen3Next support in main

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: SunnyLee219 <3294305115@qq.com>
This commit is contained in:
LeeWenquan
2025-12-03 14:17:37 +08:00
committed by GitHub
parent 3f81c4bb25
commit 38bd95229f
4 changed files with 7 additions and 3 deletions

View File

@@ -24,6 +24,7 @@ Run `pytest tests/e2e/multicard/test_qwen3_next.py`.
import os
from unittest.mock import patch
import pytest
from modelscope import snapshot_download # type: ignore
from tests.e2e.conftest import VllmRunner
@@ -63,6 +64,7 @@ def test_models_distributed_Qwen3_NEXT_TP4_FULL_DECODE_ONLY():
del vllm_model
@pytest.mark.skip
def test_models_distributed_Qwen3_NEXT_MTP_TP4_SIMILARITY():
example_prompts = [
"Hello, my name is",
@@ -113,6 +115,7 @@ def test_models_distributed_Qwen3_NEXT_MTP_TP4_SIMILARITY():
# TODO: will conduct accuracy verification after the subsequent version becomes stable
@pytest.mark.skip
@patch.dict(os.environ, {"HCCL_BUFFSIZE": "1024"})
def test_models_distributed_Qwen3_NEXT_W8A8DYNAMIC_WITH_EP():
example_prompts = [