Skip to content

Add Qwen3.5-2B (support vision and text input) #179

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
srechase-aws merged 9 commits into from
Jul 28, 2026
Merged

Add Qwen3.5-2B (support vision and text input) #179

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
530f40d
Add Qwen3.5-2B contrib model with hybrid DeltaNet + full attention
Jul 10, 2026
580161a
Qwen3.5-2B: mark VL path as WIP; keep text-only as validated
Jul 10, 2026
3b94348
Qwen3.5-2B: wire VL end-to-end (image → text)
Jul 10, 2026
801aa94
Qwen3.5-2B: multi-size VL benchmark; enable bucketed CTE for VL
Jul 10, 2026
1da7478
Qwen3.5-2B: trace vision encoder to Neuron; TTFT ~2× faster
Jul 10, 2026
baad57e
Qwen3.5-2B: 2x2 spatial tiling for oversized vision inputs
Jul 10, 2026
1f86427
Qwen3.5-2B: use actual toolchain versions in docs/comments
Jul 13, 2026
7b1a104
Qwen3.5-2B: add TP-sharded vision-encoder compile path
Jul 13, 2026
0b0aa56
Qwen3.5-2B: add TP=4 benchmark numbers to README
Jul 15, 2026
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
374 changes: 374 additions & 0 deletions contrib/models/Qwen3.5-2B/README.md
View file
Open in desktop

Large diffs are not rendered by default.

41 changes: 41 additions & 0 deletions contrib/models/Qwen3.5-2B/src/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0

from src.modeling_qwen35 import (
NeuronGatedDeltaNet,
NeuronQwen35Attention,
NeuronQwen35DecoderLayer,
NeuronQwen35ForCausalLM,
NeuronQwen35Model,
Qwen35DecoderModelInstance,
Qwen35InferenceConfig,
Qwen35MLP,
Qwen35ModelWrapper,
)
from src.modeling_qwen35_vision import (
NeuronQwen35VisionForImageEncoding,
NeuronQwen35VisionModel,
)
from src.modeling_qwen35_vl import (
NeuronQwen35VLForCausalLM,
Qwen35VLInferenceConfig,
)

__all__ = [
# Text decoder
"NeuronGatedDeltaNet",
"NeuronQwen35Attention",
"NeuronQwen35DecoderLayer",
"NeuronQwen35ForCausalLM",
"NeuronQwen35Model",
"Qwen35DecoderModelInstance",
"Qwen35InferenceConfig",
"Qwen35MLP",
"Qwen35ModelWrapper",
# Vision encoder
"NeuronQwen35VisionForImageEncoding",
"NeuronQwen35VisionModel",
# Vision-language
"NeuronQwen35VLForCausalLM",
"Qwen35VLInferenceConfig",
]
Loading