Skip to content

[Model] Add qwen3Next support in Main #4596

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Dec 3, 2025
+7 −3
Merged

[Model] Add qwen3Next support in Main #4596

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
ab68260
fix qwen3Next
SunnyLee151064 Dec 1, 2025
30648d5
Add qwen3Next CI
SunnyLee151064 Dec 1, 2025
2cb8b8f
Skip e2e
SunnyLee151064 Dec 2, 2025
3a1773a
Skip e2e
SunnyLee151064 Dec 2, 2025
e31afcd
Skip e2e
SunnyLee151064 Dec 2, 2025
c5ece48
Merge branch 'main' into fix_qwen3Next
SunnyLee151064 Dec 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/_e2e_test.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -286,4 +286,4 @@ jobs:
VLLM_USE_MODELSCOPE: True
run: |
. /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
#pytest -sv tests/e2e/multicard/test_qwen3_next.py
pytest -sv tests/e2e/multicard/test_qwen3_next.py
3 changes: 3 additions & 0 deletions tests/e2e/multicard/test_qwen3_next.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@
import os
from unittest.mock import patch

import pytest
from modelscope import snapshot_download # type: ignore

from tests.e2e.conftest import VllmRunner
Expand Down Expand Up @@ -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",
Expand Down Expand Up @@ -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 = [
Expand Down
3 changes: 2 additions & 1 deletion vllm_ascend/ops/triton/mamba/casual_conv1d.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
# and https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/layers/mamba/ops/causal_conv1d.py
# mypy: ignore-errors

from typing import Optional, Union
from typing import Any, Optional, Union

import torch
import torch.nn.functional as F
Expand Down Expand Up @@ -72,6 +72,7 @@ def causal_conv1d_fn(
conv_states: Optional[torch.Tensor] = None,
activation: Optional[str] = "silu",
pad_slot_id: int = PAD_SLOT_ID,
metadata: Optional[Any] = None,
):
"""
x: (batch, dim, seqlen) or (dim,cu_seq_len) for varlen
Expand Down
2 changes: 1 addition & 1 deletion vllm_ascend/patch/worker/patch_triton.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,4 @@
vllm.model_executor.layers.mamba.ops.causal_conv1d.causal_conv1d_fn = causal_conv1d_fn
vllm.model_executor.layers.fla.ops.fused_recurrent.fused_recurrent_gated_delta_rule_fwd_kernel = fused_recurrent_gated_delta_rule_fwd_kernel
vllm.model_executor.layers.fla.ops.layernorm_guard.LayerNormFn = LayerNormFn
vllm.model_executor.layers.fla.ops.chunk.chunk_gated_delta_rule = chunk_gated_delta_rule
vllm.model_executor.layers.fla.ops.chunk_gated_delta_rule = chunk_gated_delta_rule
Loading