Skip to content

Commit 9322357

Browse files
apsonawaneapsonawane
authored
Add Qwen3.5 VL model recipes (0.8B, 2B, 4B, 9B) (#268)
1 parent 84382ca commit 9322357

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

68 files changed

+8384
-0
lines changed

‎Qwen-Qwen3.5-0.8B/LICENSE‎

Lines changed: 190 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,190 @@
1+
Apache License
2+
Version 2.0, January 2004
3+
http://www.apache.org/licenses/
4+
5+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6+
7+
1. Definitions.
8+
9+
"License" shall mean the terms and conditions for use, reproduction,
10+
and distribution as defined by Sections 1 through 9 of this document.
11+
12+
"Licensor" shall mean the copyright owner or entity authorized by
13+
the copyright owner that is granting the License.
14+
15+
"Legal Entity" shall mean the union of the acting entity and all
16+
other entities that control, are controlled by, or are under common
17+
control with that entity. For the purposes of this definition,
18+
"control" means (i) the power, direct or indirect, to cause the
19+
direction or management of such entity, whether by contract or
20+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
21+
outstanding shares, or (iii) beneficial ownership of such entity.
22+
23+
"You" (or "Your") shall mean an individual or Legal Entity
24+
exercising permissions granted by this License.
25+
26+
"Source" form shall mean the preferred form for making modifications,
27+
including but not limited to software source code, documentation
28+
source, and configuration files.
29+
30+
"Object" form shall mean any form resulting from mechanical
31+
transformation or translation of a Source form, including but
32+
not limited to compiled object code, generated documentation,
33+
and conversions to other media types.
34+
35+
"Work" shall mean the work of authorship, whether in Source or
36+
Object form, made available under the License, as indicated by a
37+
copyright notice that is included in or attached to the work
38+
(an example is provided in the Appendix below).
39+
40+
"Derivative Works" shall mean any work, whether in Source or Object
41+
form, that is based on (or derived from) the Work and for which the
42+
editorial revisions, annotations, elaborations, or other modifications
43+
represent, as a whole, an original work of authorship. For the purposes
44+
of this License, Derivative Works shall not include works that remain
45+
separable from, or merely link (or bind by name) to the interfaces of,
46+
the Work and Derivative Works thereof.
47+
48+
"Contribution" shall mean any work of authorship, including
49+
the original version of the Work and any modifications or additions
50+
to that Work or Derivative Works thereof, that is intentionally
51+
submitted to the Licensor for inclusion in the Work by the copyright owner
52+
or by an individual or Legal Entity authorized to submit on behalf of
53+
the copyright owner. For the purposes of this definition, "submitted"
54+
means any form of electronic, verbal, or written communication sent
55+
to the Licensor or its representatives, including but not limited to
56+
communication on electronic mailing lists, source code control systems,
57+
and issue tracking systems that are managed by, or on behalf of, the
58+
Licensor for the purpose of discussing and improving the Work, but
59+
excluding communication that is conspicuously marked or otherwise
60+
designated in writing by the copyright owner as "Not a Contribution."
61+
62+
"Contributor" shall mean Licensor and any individual or Legal Entity
63+
on behalf of whom a Contribution has been received by the Licensor and
64+
subsequently incorporated within the Work.
65+
66+
2. Grant of Copyright License. Subject to the terms and conditions of
67+
this License, each Contributor hereby grants to You a perpetual,
68+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69+
copyright license to reproduce, prepare Derivative Works of,
70+
publicly display, publicly perform, sublicense, and distribute the
71+
Work and such Derivative Works in Source or Object form.
72+
73+
3. Grant of Patent License. Subject to the terms and conditions of
74+
this License, each Contributor hereby grants to You a perpetual,
75+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76+
(except as stated in this section) patent license to make, have made,
77+
use, offer to sell, sell, import, and otherwise transfer the Work,
78+
where such license applies only to those patent claims licensable
79+
by such Contributor that are necessarily infringed by their
80+
Contribution(s) alone or by combination of their Contribution(s)
81+
with the Work to which such Contribution(s) was submitted. If You
82+
institute patent litigation against any entity (including a
83+
cross-claim or counterclaim in a lawsuit) alleging that the Work
84+
or a Contribution incorporated within the Work constitutes direct
85+
or contributory patent infringement, then any patent licenses
86+
granted to You under this License for that Work shall terminate
87+
as of the date such litigation is filed.
88+
89+
4. Redistribution. You may reproduce and distribute copies of the
90+
Work or Derivative Works thereof in any medium, with or without
91+
modifications, and in Source or Object form, provided that You
92+
meet the following conditions:
93+
94+
(a) You must give any other recipients of the Work or
95+
Derivative Works a copy of this License; and
96+
97+
(b) You must cause any modified files to carry prominent notices
98+
stating that You changed the files; and
99+
100+
(c) You must retain, in the Source form of any Derivative Works
101+
that You distribute, all copyright, patent, trademark, and
102+
attribution notices from the Source form of the Work,
103+
excluding those notices that do not pertain to any part of
104+
the Derivative Works; and
105+
106+
(d) If the Work includes a "NOTICE" text file as part of its
107+
distribution, then any Derivative Works that You distribute must
108+
include a readable copy of the attribution notices contained
109+
within such NOTICE file, excluding any notices that do not
110+
pertain to any part of the Derivative Works, in at least one
111+
of the following places: within a NOTICE text file distributed
112+
as part of the Derivative Works; within the Source form or
113+
documentation, if provided along with the Derivative Works; or,
114+
within a display generated by the Derivative Works, if and
115+
wherever such third-party notices normally appear. The contents
116+
of the NOTICE file are for informational purposes only and
117+
do not modify the License. You may add Your own attribution
118+
notices within Derivative Works that You distribute, alongside
119+
or as an addendum to the NOTICE text from the Work, provided
120+
that such additional attribution notices cannot be construed
121+
as modifying the License.
122+
123+
You may add Your own copyright statement to Your modifications and
124+
may provide additional or different license terms and conditions
125+
for use, reproduction, or distribution of Your modifications, or
126+
for any such Derivative Works as a whole, provided Your use,
127+
reproduction, and distribution of the Work otherwise complies with
128+
the conditions stated in this License.
129+
130+
5. Submission of Contributions. Unless You explicitly state otherwise,
131+
any Contribution intentionally submitted for inclusion in the Work
132+
by You to the Licensor shall be under the terms and conditions of
133+
this License, without any additional terms or conditions.
134+
Notwithstanding the above, nothing herein shall supersede or modify
135+
the terms of any separate license agreement you may have executed
136+
with Licensor regarding such Contributions.
137+
138+
6. Trademarks. This License does not grant permission to use the trade
139+
names, trademarks, service marks, or product names of the Licensor,
140+
except as required for reasonable and customary use in describing the
141+
origin of the Work and reproducing the content of the NOTICE file.
142+
143+
7. Disclaimer of Warranty. Unless required by applicable law or
144+
agreed to in writing, Licensor provides the Work (and each
145+
Contributor provides its Contributions) on an "AS IS" BASIS,
146+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147+
implied, including, without limitation, any warranties or conditions
148+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149+
PARTICULAR PURPOSE. You are solely responsible for determining the
150+
appropriateness of using or redistributing the Work and assume any
151+
risks associated with Your exercise of permissions under this License.
152+
153+
8. Limitation of Liability. In no event and under no legal theory,
154+
whether in tort (including negligence), contract, or otherwise,
155+
unless required by applicable law (such as deliberate and grossly
156+
negligent acts) or agreed to in writing, shall any Contributor be
157+
liable to You for damages, including any direct, indirect, special,
158+
incidental, or consequential damages of any character arising as a
159+
result of this License or out of the use or inability to use the
160+
Work (including but not limited to damages for loss of goodwill,
161+
work stoppage, computer failure or malfunction, or any and all
162+
other commercial damages or losses), even if such Contributor
163+
has been advised of the possibility of such damages.
164+
165+
9. Accepting Warranty or Additional Liability. While redistributing
166+
the Work or Derivative Works thereof, You may choose to offer,
167+
and charge a fee for, acceptance of support, warranty, indemnity,
168+
or other liability obligations and/or rights consistent with this
169+
License. However, in accepting such obligations, You may act only
170+
on Your own behalf and on Your sole responsibility, not on behalf
171+
of any other Contributor, and only if You agree to indemnify,
172+
defend, and hold each Contributor harmless for any liability
173+
incurred by, or claims asserted against, such Contributor by reason
174+
of your accepting any such warranty or additional liability.
175+
176+
END OF TERMS AND CONDITIONS
177+
178+
Copyright (c) Microsoft Corporation.
179+
180+
Licensed under the Apache License, Version 2.0 (the "License");
181+
you may not use this file except in compliance with the License.
182+
You may obtain a copy of the License at
183+
184+
http://www.apache.org/licenses/LICENSE-2.0
185+
186+
Unless required by applicable law or agreed to in writing, software
187+
distributed under the License is distributed on an "AS IS" BASIS,
188+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
189+
See the License for the specific language governing permissions and
190+
limitations under the License.

‎Qwen-Qwen3.5-0.8B/builtin/.gitignore‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
# Generated model artifacts
2+
models/
3+
4+
# Python bytecode
5+
__pycache__/
6+
*.pyc
7+
8+
# Olive cache
9+
.olive-cache/

‎Qwen-Qwen3.5-0.8B/builtin/README.md‎

Lines changed: 99 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,99 @@
1+
# Qwen3.5-0.8B ONNX Runtime GenAI Example
2+
3+
This example demonstrates how to convert [Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) vision-language model to ONNX format using Olive and run inference with ONNX Runtime GenAI.
4+
5+
Qwen3.5 is a hybrid architecture combining GatedDeltaNet linear attention layers with standard full attention layers. The pipeline exports three sub-models (vision encoder, text embedding, text decoder) and applies graph optimizations. For CPU, all three sub-models are quantized to INT4. For CUDA, the vision encoder and embedding use FP16 while the text decoder uses INT4.
6+
7+
## Prerequisites
8+
9+
```bash
10+
pip install -r requirements.txt
11+
```
12+
13+
Install ONNX Runtime GenAI:
14+
15+
| Device | Install Command |
16+
|--------|-----------------|
17+
| CPU | `pip install onnxruntime-genai --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/pypi/simple` |
18+
| GPU (CUDA) | `pip install onnxruntime-genai-cuda --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/pypi/simple` |
19+
20+
## Steps
21+
22+
### 1. Export & Optimize Models
23+
24+
**CPU (INT4 quantized):**
25+
26+
```bash
27+
python optimize.py --config-dir cpu_and_mobile --device cpu
28+
```
29+
30+
**CUDA (FP16 vision/embedding + INT4 text decoder):**
31+
32+
```bash
33+
python optimize.py --config-dir cuda --device gpu
34+
```
35+
36+
This runs three Olive pipelines:
37+
- **embedding.json** — Exports the embedding fusion model (token embedding + image feature scatter)
38+
- **vision.json** — Exports the vision encoder (packed patches → image features)
39+
- **text.json** — Exports the text decoder via ModelBuilder (hybrid GatedDeltaNet + full attention, INT4)
40+
41+
Then generates `genai_config.json` and `processor_config.json` for the ORT GenAI runtime.
42+
43+
### 2. Output Structure
44+
45+
```
46+
cpu_and_mobile/models/ # or cuda/models/
47+
├── embedding.onnx # Embedding fusion model
48+
├── embedding.onnx.data
49+
├── vision.onnx # Vision encoder
50+
├── vision.onnx.data
51+
├── text.onnx # Text decoder (hybrid)
52+
├── text.onnx.data
53+
├── genai_config.json # Runtime configuration
54+
├── processor_config.json # Image preprocessing
55+
├── tokenizer.json
56+
└── tokenizer_config.json
57+
```
58+
59+
### 3. Run Inference
60+
61+
```bash
62+
# Text-only
63+
python inference.py --prompt "What is the capital of France?"
64+
65+
# Image + text
66+
python inference.py --image photo.jpg --prompt "Describe this image"
67+
68+
# Interactive mode
69+
python inference.py --interactive
70+
71+
# CUDA model
72+
python inference.py --model_path cuda/models --prompt "Hello"
73+
```
74+
75+
Alternatively, use the built-in GenAI multimodal demo:
76+
77+
```bash
78+
python -m onnxruntime_genai.models.model_mm -m cpu_and_mobile/models --max_length 4096
79+
```
80+
81+
### 4. Evaluate on AI2D
82+
83+
Run the AI2D (diagram understanding) benchmark to measure accuracy:
84+
85+
```bash
86+
# ONNX only (100 samples, default)
87+
python eval.py
88+
89+
# Compare ONNX vs PyTorch side-by-side
90+
python eval.py --pytorch_model Qwen/Qwen3.5-0.8B
91+
92+
# Larger evaluation
93+
python eval.py --num_samples 500 --pytorch_model Qwen/Qwen3.5-0.8B
94+
95+
# CUDA model
96+
python eval.py --model_path cuda/models
97+
```
98+
99+
The eval script reports per-sample accuracy, average latency, and an ONNX-vs-PyTorch comparison summary.

‎Qwen-Qwen3.5-0.8B/builtin/codes/__init__.py‎

Whitespace-only changes.

0 commit comments

Comments
 (0)