Skip to content

Commit 5cbf07e

Browse files
sayakpaulsayakpaul
authored
Merge branch 'main' into respect-hf-quantizer-cache-warmup
2 parents 223bb6a + 1082c46 commit 5cbf07e

Some content is hidden

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

54 files changed

+6666
-209
lines changed

‎.github/workflows/benchmark.yml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ jobs:
2525
group: aws-g6e-4xlarge
2626
container:
2727
image: diffusers/diffusers-pytorch-cuda
28-
options: --shm-size "16gb" --ipc host --gpus 0
28+
options: --shm-size "16gb" --ipc host --gpus all
2929
steps:
3030
- name: Checkout diffusers
3131
uses: actions/checkout@v3

‎.github/workflows/nightly_tests.yml‎

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -61,7 +61,7 @@ jobs:
6161
group: aws-g4dn-2xlarge
6262
container:
6363
image: diffusers/diffusers-pytorch-cuda
64-
options: --shm-size "16gb" --ipc host --gpus 0
64+
options: --shm-size "16gb" --ipc host --gpus all
6565
steps:
6666
- name: Checkout diffusers
6767
uses: actions/checkout@v3
@@ -107,7 +107,7 @@ jobs:
107107
group: aws-g4dn-2xlarge
108108
container:
109109
image: diffusers/diffusers-pytorch-cuda
110-
options: --shm-size "16gb" --ipc host --gpus 0
110+
options: --shm-size "16gb" --ipc host --gpus all
111111
defaults:
112112
run:
113113
shell: bash
@@ -178,7 +178,7 @@ jobs:
178178

179179
container:
180180
image: diffusers/diffusers-pytorch-cuda
181-
options: --gpus 0 --shm-size "16gb" --ipc host
181+
options: --gpus all --shm-size "16gb" --ipc host
182182

183183
steps:
184184
- name: Checkout diffusers
@@ -222,7 +222,7 @@ jobs:
222222
group: aws-g6e-xlarge-plus
223223
container:
224224
image: diffusers/diffusers-pytorch-cuda
225-
options: --shm-size "16gb" --ipc host --gpus 0
225+
options: --shm-size "16gb" --ipc host --gpus all
226226
steps:
227227
- name: Checkout diffusers
228228
uses: actions/checkout@v3
@@ -270,7 +270,7 @@ jobs:
270270
group: aws-g4dn-2xlarge
271271
container:
272272
image: diffusers/diffusers-pytorch-minimum-cuda
273-
options: --shm-size "16gb" --ipc host --gpus 0
273+
options: --shm-size "16gb" --ipc host --gpus all
274274
defaults:
275275
run:
276276
shell: bash
@@ -333,7 +333,7 @@ jobs:
333333
additional_deps: ["peft"]
334334
- backend: "gguf"
335335
test_location: "gguf"
336-
additional_deps: ["peft"]
336+
additional_deps: ["peft", "kernels"]
337337
- backend: "torchao"
338338
test_location: "torchao"
339339
additional_deps: []
@@ -344,7 +344,7 @@ jobs:
344344
group: aws-g6e-xlarge-plus
345345
container:
346346
image: diffusers/diffusers-pytorch-cuda
347-
options: --shm-size "20gb" --ipc host --gpus 0
347+
options: --shm-size "20gb" --ipc host --gpus all
348348
steps:
349349
- name: Checkout diffusers
350350
uses: actions/checkout@v3
@@ -396,7 +396,7 @@ jobs:
396396
group: aws-g6e-xlarge-plus
397397
container:
398398
image: diffusers/diffusers-pytorch-cuda
399-
options: --shm-size "20gb" --ipc host --gpus 0
399+
options: --shm-size "20gb" --ipc host --gpus all
400400
steps:
401401
- name: Checkout diffusers
402402
uses: actions/checkout@v3

‎.github/workflows/pr_tests_gpu.yml‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -118,7 +118,7 @@ jobs:
118118
group: aws-g4dn-2xlarge
119119
container:
120120
image: diffusers/diffusers-pytorch-cuda
121-
options: --shm-size "16gb" --ipc host --gpus 0
121+
options: --shm-size "16gb" --ipc host --gpus all
122122
steps:
123123
- name: Checkout diffusers
124124
uses: actions/checkout@v3
@@ -183,7 +183,7 @@ jobs:
183183
group: aws-g4dn-2xlarge
184184
container:
185185
image: diffusers/diffusers-pytorch-cuda
186-
options: --shm-size "16gb" --ipc host --gpus 0
186+
options: --shm-size "16gb" --ipc host --gpus all
187187
defaults:
188188
run:
189189
shell: bash
@@ -253,7 +253,7 @@ jobs:
253253

254254
container:
255255
image: diffusers/diffusers-pytorch-cuda
256-
options: --gpus 0 --shm-size "16gb" --ipc host
256+
options: --gpus all --shm-size "16gb" --ipc host
257257
steps:
258258
- name: Checkout diffusers
259259
uses: actions/checkout@v3

‎.github/workflows/push_tests.yml‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -64,7 +64,7 @@ jobs:
6464
group: aws-g4dn-2xlarge
6565
container:
6666
image: diffusers/diffusers-pytorch-cuda
67-
options: --shm-size "16gb" --ipc host --gpus 0
67+
options: --shm-size "16gb" --ipc host --gpus all
6868
steps:
6969
- name: Checkout diffusers
7070
uses: actions/checkout@v3
@@ -109,7 +109,7 @@ jobs:
109109
group: aws-g4dn-2xlarge
110110
container:
111111
image: diffusers/diffusers-pytorch-cuda
112-
options: --shm-size "16gb" --ipc host --gpus 0
112+
options: --shm-size "16gb" --ipc host --gpus all
113113
defaults:
114114
run:
115115
shell: bash
@@ -167,7 +167,7 @@ jobs:
167167

168168
container:
169169
image: diffusers/diffusers-pytorch-cuda
170-
options: --gpus 0 --shm-size "16gb" --ipc host
170+
options: --gpus all --shm-size "16gb" --ipc host
171171

172172
steps:
173173
- name: Checkout diffusers
@@ -210,7 +210,7 @@ jobs:
210210

211211
container:
212212
image: diffusers/diffusers-pytorch-xformers-cuda
213-
options: --gpus 0 --shm-size "16gb" --ipc host
213+
options: --gpus all --shm-size "16gb" --ipc host
214214

215215
steps:
216216
- name: Checkout diffusers
@@ -252,7 +252,7 @@ jobs:
252252

253253
container:
254254
image: diffusers/diffusers-pytorch-cuda
255-
options: --gpus 0 --shm-size "16gb" --ipc host
255+
options: --gpus all --shm-size "16gb" --ipc host
256256
steps:
257257
- name: Checkout diffusers
258258
uses: actions/checkout@v3

‎.github/workflows/release_tests_fast.yml‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -62,7 +62,7 @@ jobs:
6262
group: aws-g4dn-2xlarge
6363
container:
6464
image: diffusers/diffusers-pytorch-cuda
65-
options: --shm-size "16gb" --ipc host --gpus 0
65+
options: --shm-size "16gb" --ipc host --gpus all
6666
steps:
6767
- name: Checkout diffusers
6868
uses: actions/checkout@v3
@@ -107,7 +107,7 @@ jobs:
107107
group: aws-g4dn-2xlarge
108108
container:
109109
image: diffusers/diffusers-pytorch-cuda
110-
options: --shm-size "16gb" --ipc host --gpus 0
110+
options: --shm-size "16gb" --ipc host --gpus all
111111
defaults:
112112
run:
113113
shell: bash
@@ -163,7 +163,7 @@ jobs:
163163
group: aws-g4dn-2xlarge
164164
container:
165165
image: diffusers/diffusers-pytorch-minimum-cuda
166-
options: --shm-size "16gb" --ipc host --gpus 0
166+
options: --shm-size "16gb" --ipc host --gpus all
167167
defaults:
168168
run:
169169
shell: bash
@@ -222,7 +222,7 @@ jobs:
222222

223223
container:
224224
image: diffusers/diffusers-pytorch-cuda
225-
options: --gpus 0 --shm-size "16gb" --ipc host
225+
options: --gpus all --shm-size "16gb" --ipc host
226226

227227
steps:
228228
- name: Checkout diffusers
@@ -265,7 +265,7 @@ jobs:
265265

266266
container:
267267
image: diffusers/diffusers-pytorch-xformers-cuda
268-
options: --gpus 0 --shm-size "16gb" --ipc host
268+
options: --gpus all --shm-size "16gb" --ipc host
269269

270270
steps:
271271
- name: Checkout diffusers
@@ -307,7 +307,7 @@ jobs:
307307

308308
container:
309309
image: diffusers/diffusers-pytorch-cuda
310-
options: --gpus 0 --shm-size "16gb" --ipc host
310+
options: --gpus all --shm-size "16gb" --ipc host
311311

312312
steps:
313313
- name: Checkout diffusers

‎.github/workflows/run_tests_from_a_pr.yml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ jobs:
3030
group: aws-g4dn-2xlarge
3131
container:
3232
image: ${{ github.event.inputs.docker_image }}
33-
options: --gpus 0 --privileged --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
33+
options: --gpus all --privileged --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
3434

3535
steps:
3636
- name: Validate test files input

‎.github/workflows/ssh-runner.yml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -31,7 +31,7 @@ jobs:
3131
group: "${{ github.event.inputs.runner_type }}"
3232
container:
3333
image: ${{ github.event.inputs.docker_image }}
34-
options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0 --privileged
34+
options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus all --privileged
3535

3636
steps:
3737
- name: Checkout diffusers

‎docs/source/en/_toctree.yml‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -366,6 +366,8 @@
366366
title: PixArtTransformer2DModel
367367
- local: api/models/prior_transformer
368368
title: PriorTransformer
369+
- local: api/models/qwenimage_transformer2d
370+
title: QwenImageTransformer2DModel
369371
- local: api/models/sana_transformer2d
370372
title: SanaTransformer2DModel
371373
- local: api/models/sd3_transformer2d
@@ -418,6 +420,8 @@
418420
title: AutoencoderKLMagvit
419421
- local: api/models/autoencoderkl_mochi
420422
title: AutoencoderKLMochi
423+
- local: api/models/autoencoderkl_qwenimage
424+
title: AutoencoderKLQwenImage
421425
- local: api/models/autoencoder_kl_wan
422426
title: AutoencoderKLWan
423427
- local: api/models/consistency_decoder_vae
@@ -554,6 +558,8 @@
554558
title: PixArt-α
555559
- local: api/pipelines/pixart_sigma
556560
title: PixArt-Σ
561+
- local: api/pipelines/qwenimage
562+
title: QwenImage
557563
- local: api/pipelines/sana
558564
title: Sana
559565
- local: api/pipelines/sana_sprint

‎docs/source/en/api/loaders/lora.md‎

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -30,6 +30,7 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
3030
- [`CogView4LoraLoaderMixin`] provides similar functions for [CogView4](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogview4).
3131
- [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
3232
- [`HiDreamImageLoraLoaderMixin`] provides similar functions for [HiDream Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hidream)
33+
- [`QwenImageLoraLoaderMixin`] provides similar functions for [Qwen Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwen)
3334
- [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
3435

3536
<Tip>
@@ -105,6 +106,10 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
105106

106107
[[autodoc]] loaders.lora_pipeline.HiDreamImageLoraLoaderMixin
107108

109+
## QwenImageLoraLoaderMixin
110+
111+
[[autodoc]] loaders.lora_pipeline.QwenImageLoraLoaderMixin
112+
108113
## LoraBaseMixin
109114

110115
[[autodoc]] loaders.lora_base.LoraBaseMixin

‎docs/source/en/api/models/autoencoderkl_qwenimage.md‎

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
2+
3+
Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
4+
the License. You may obtain a copy of the License at
5+
6+
http://www.apache.org/licenses/LICENSE-2.0
7+
8+
Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
9+
an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
10+
specific language governing permissions and limitations under the License. -->
11+
12+
# AutoencoderKLQwenImage
13+
14+
The model can be loaded with the following code snippet.
15+
16+
```python
17+
from diffusers import AutoencoderKLQwenImage
18+
19+
vae = AutoencoderKLQwenImage.from_pretrained("Qwen/QwenImage-20B", subfolder="vae")
20+
```
21+
22+
## AutoencoderKLQwenImage
23+
24+
[[autodoc]] AutoencoderKLQwenImage
25+
- decode
26+
- encode
27+
- all
28+
29+
## AutoencoderKLOutput
30+
31+
[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
32+
33+
## DecoderOutput
34+
35+
[[autodoc]] models.autoencoders.vae.DecoderOutput

0 commit comments

Comments
 (0)