cache-dit 0.1.0__tar.gz → 0.1.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of cache-dit might be problematic. Click here for more details.

Files changed (74) hide show
  1. {cache_dit-0.1.0 → cache_dit-0.1.1}/PKG-INFO +10 -10
  2. {cache_dit-0.1.0 → cache_dit-0.1.1}/README.md +9 -9
  3. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/_version.py +2 -2
  4. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/__init__.py +3 -1
  5. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit.egg-info/PKG-INFO +10 -10
  6. {cache_dit-0.1.0 → cache_dit-0.1.1}/.github/workflows/issue.yml +0 -0
  7. {cache_dit-0.1.0 → cache_dit-0.1.1}/.gitignore +0 -0
  8. {cache_dit-0.1.0 → cache_dit-0.1.1}/.pre-commit-config.yaml +0 -0
  9. {cache_dit-0.1.0 → cache_dit-0.1.1}/CONTRIBUTE.md +0 -0
  10. {cache_dit-0.1.0 → cache_dit-0.1.1}/LICENSE +0 -0
  11. {cache_dit-0.1.0 → cache_dit-0.1.1}/MANIFEST.in +0 -0
  12. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F12B12S4_R0.2_S16.png +0 -0
  13. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F12B16S4_R0.08_S6.png +0 -0
  14. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F16B16S2_R0.2_S14.png +0 -0
  15. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F16B16S4_R0.2_S13.png +0 -0
  16. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F1B0S1_R0.08_S11.png +0 -0
  17. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F1B0S1_R0.2_S19.png +0 -0
  18. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F8B0S2_R0.12_S12.png +0 -0
  19. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F8B16S1_R0.2_S18.png +0 -0
  20. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F8B8S1_R0.08_S9.png +0 -0
  21. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F8B8S1_R0.12_S12.png +0 -0
  22. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCACHE_F8B8S1_R0.15_S15.png +0 -0
  23. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCache.png +0 -0
  24. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png +0 -0
  25. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png +0 -0
  26. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png +0 -0
  27. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png +0 -0
  28. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.07_P52.3_T12.53s.png +0 -0
  29. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.08_P52.4_T12.52s.png +0 -0
  30. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.09_P59.2_T10.81s.png +0 -0
  31. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.12_P59.5_T10.76s.png +0 -0
  32. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.12_P63.0_T9.90s.png +0 -0
  33. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.1_P62.8_T9.95s.png +0 -0
  34. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png +0 -0
  35. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBPRUNE_F1B0_R0.3_P63.1_T9.79s.png +0 -0
  36. {cache_dit-0.1.0 → cache_dit-0.1.1}/assets/NONE_R0.08_S0.png +0 -0
  37. {cache_dit-0.1.0 → cache_dit-0.1.1}/bench/.gitignore +0 -0
  38. {cache_dit-0.1.0 → cache_dit-0.1.1}/bench/bench.py +0 -0
  39. {cache_dit-0.1.0 → cache_dit-0.1.1}/docs/.gitignore +0 -0
  40. {cache_dit-0.1.0 → cache_dit-0.1.1}/examples/.gitignore +0 -0
  41. {cache_dit-0.1.0 → cache_dit-0.1.1}/examples/run_flux.py +0 -0
  42. {cache_dit-0.1.0 → cache_dit-0.1.1}/pyproject.toml +0 -0
  43. {cache_dit-0.1.0 → cache_dit-0.1.1}/pytest.ini +0 -0
  44. {cache_dit-0.1.0 → cache_dit-0.1.1}/requirements.txt +0 -0
  45. {cache_dit-0.1.0 → cache_dit-0.1.1}/setup.cfg +0 -0
  46. {cache_dit-0.1.0 → cache_dit-0.1.1}/setup.py +0 -0
  47. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/__init__.py +0 -0
  48. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dual_block_cache/__init__.py +0 -0
  49. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dual_block_cache/cache_context.py +0 -0
  50. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters/__init__.py +0 -0
  51. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters/cogvideox.py +0 -0
  52. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters/flux.py +0 -0
  53. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters/mochi.py +0 -0
  54. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dynamic_block_prune/__init__.py +0 -0
  55. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dynamic_block_prune/diffusers_adapters/__init__.py +0 -0
  56. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dynamic_block_prune/diffusers_adapters/cogvideox.py +0 -0
  57. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dynamic_block_prune/diffusers_adapters/flux.py +0 -0
  58. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dynamic_block_prune/diffusers_adapters/mochi.py +0 -0
  59. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/dynamic_block_prune/prune_context.py +0 -0
  60. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/first_block_cache/__init__.py +0 -0
  61. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/first_block_cache/cache_context.py +0 -0
  62. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/first_block_cache/diffusers_adapters/__init__.py +0 -0
  63. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/first_block_cache/diffusers_adapters/cogvideox.py +0 -0
  64. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/first_block_cache/diffusers_adapters/flux.py +0 -0
  65. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/first_block_cache/diffusers_adapters/mochi.py +0 -0
  66. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/first_block_cache/diffusers_adapters/wan.py +0 -0
  67. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/taylorseer.py +0 -0
  68. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/utils.py +0 -0
  69. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/logger.py +0 -0
  70. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/primitives.py +0 -0
  71. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit.egg-info/SOURCES.txt +0 -0
  72. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit.egg-info/dependency_links.txt +0 -0
  73. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit.egg-info/requires.txt +0 -0
  74. {cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit.egg-info/top_level.txt +0 -0
{cache_dit-0.1.0 → cache_dit-0.1.1}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: cache_dit
3
- Version: 0.1.0
3
+ Version: 0.1.1
4
4
  Summary: ⚡️DBCache: A Training-free UNet-style Cache Acceleration for Diffusion Transformers
5
5
  Author: DefTruth, vipshop.com, etc.
6
6
  Maintainer: DefTruth, vipshop.com, etc
@@ -37,13 +37,13 @@ Dynamic: requires-python
37
37
  <p align="center">
38
38
  <h3>⚡️DBCache: A Training-free UNet-style Cache Acceleration for <br>Diffusion Transformers</h2>
39
39
  </p>
40
- <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCache.png >
40
+ <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCache.png >
41
41
  <div align='center'>
42
42
  <img src=https://img.shields.io/badge/Language-Python-brightgreen.svg >
43
43
  <img src=https://img.shields.io/badge/PRs-welcome-9cf.svg >
44
- <img src=https://img.shields.io/badge/Build-pass-brightgreen.svg >
44
+ <img src=https://img.shields.io/badge/PyPI-pass-brightgreen.svg >
45
45
  <img src=https://img.shields.io/badge/Python-3.10|3.11|3.12-9cf.svg >
46
- <img src=https://img.shields.io/badge/Release-v0.1.0-brightgreen.svg >
46
+ <img src=https://img.shields.io/badge/Release-v0.1.1-brightgreen.svg >
47
47
  </div>
48
48
  <p align="center">
49
49
  DeepCache requires UNet’s U-shape, but DiT lacks it. Most DiT cache accelerators are complex and not training-free. DBCache builds on FBCache to create a training-free, UNet-style cache accelerator for DiT.
@@ -69,7 +69,7 @@ Dynamic: requires-python
69
69
  |Baseline(L20x1)|F1B0 (0.08)|F1B0 (0.20)|F8B8 (0.15)|F12B12 (0.20)|F16B16 (0.20)|
70
70
  |:---:|:---:|:---:|:---:|:---:|:---:|
71
71
  |24.85s|15.59s|8.58s|15.41s|15.11s|17.74s|
72
- |<img src=https://github.com/vipshop/DBCache/blob/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F1B0S1_R0.08_S11.png width=105px> | <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F1B0S1_R0.2_S19.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F8B8S1_R0.15_S15.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F12B12S4_R0.2_S16.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F16B16S4_R0.2_S13.png width=105px>|
72
+ |<img src=https://github.com/vipshop/DBCache/raw/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F1B0S1_R0.08_S11.png width=105px> | <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F1B0S1_R0.2_S19.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F8B8S1_R0.15_S15.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F12B12S4_R0.2_S16.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F16B16S4_R0.2_S13.png width=105px>|
73
73
  |**Baseline(L20x1)**|**F1B0 (0.08)**|**F8B8 (0.12)**|**F8B12 (0.20)**|**F8B16 (0.20)**|**F8B20 (0.20)**|
74
74
  |27.85s|6.04s|5.88s|5.77s|6.01s|6.20s|
75
75
  |<img src=https://github.com/user-attachments/assets/70ea57f4-d8f2-415b-8a96-d8315974a5e6 width=105px>|<img src=https://github.com/user-attachments/assets/fc0e1a67-19cc-44aa-bf50-04696e7978a0 width=105px> |<img src=https://github.com/user-attachments/assets/d1434896-628c-436b-95ad-43c085a8629e width=105px>|<img src=https://github.com/user-attachments/assets/aaa42cd2-57de-4c4e-8bfb-913018a8251d width=105px>|<img src=https://github.com/user-attachments/assets/dc0ba2a4-ef7c-436d-8a39-67055deab92f width=105px>|<img src=https://github.com/user-attachments/assets/aede466f-61ed-4256-8df0-fecf8020c5ca width=105px>|
@@ -93,7 +93,7 @@ These case studies demonstrate that even with relatively high thresholds (such a
93
93
  |Baseline(L20x1)|Pruned(24%)|Pruned(35%)|Pruned(38%)|Pruned(45%)|Pruned(60%)|
94
94
  |:---:|:---:|:---:|:---:|:---:|:---:|
95
95
  |24.85s|19.43s|16.82s|15.95s|14.24s|10.66s|
96
- |<img src=https://github.com/vipshop/DBCache/blob/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
96
+ |<img src=https://github.com/vipshop/DBCache/raw/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
97
97
 
98
98
  <div align="center">
99
99
  <p align="center">
@@ -270,7 +270,7 @@ apply_cache_on_pipe(pipe, **cache_options)
270
270
  |Baseline(L20x1)|Pruned(24%)|Pruned(35%)|Pruned(38%)|Pruned(45%)|Pruned(60%)|
271
271
  |:---:|:---:|:---:|:---:|:---:|:---:|
272
272
  |24.85s|19.43s|16.82s|15.95s|14.24s|10.66s|
273
- |<img src=https://github.com/vipshop/DBCache/blob/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
273
+ |<img src=https://github.com/vipshop/DBCache/raw/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
274
274
 
275
275
  ## 🎉Context Parallelism
276
276
 
@@ -333,9 +333,9 @@ Otherwise, the recompile_limit error may be triggered, causing the module to fal
333
333
 
334
334
  <div id="supported"></div>
335
335
 
336
- - [🚀FLUX.1](https://github.com/vipshop/DBCache/blob/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
337
- - [🚀CogVideoX](https://github.com/vipshop/DBCache/blob/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
338
- - [🚀Mochi](https://github.com/vipshop/DBCache/blob/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
336
+ - [🚀FLUX.1](https://github.com/vipshop/DBCache/raw/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
337
+ - [🚀CogVideoX](https://github.com/vipshop/DBCache/raw/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
338
+ - [🚀Mochi](https://github.com/vipshop/DBCache/raw/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
339
339
 
340
340
  ## 👋Contribute
341
341
  <div id="contribute"></div>
{cache_dit-0.1.0 → cache_dit-0.1.1}/README.md RENAMED
@@ -2,13 +2,13 @@
2
2
  <p align="center">
3
3
  <h3>⚡️DBCache: A Training-free UNet-style Cache Acceleration for <br>Diffusion Transformers</h2>
4
4
  </p>
5
- <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCache.png >
5
+ <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCache.png >
6
6
  <div align='center'>
7
7
  <img src=https://img.shields.io/badge/Language-Python-brightgreen.svg >
8
8
  <img src=https://img.shields.io/badge/PRs-welcome-9cf.svg >
9
- <img src=https://img.shields.io/badge/Build-pass-brightgreen.svg >
9
+ <img src=https://img.shields.io/badge/PyPI-pass-brightgreen.svg >
10
10
  <img src=https://img.shields.io/badge/Python-3.10|3.11|3.12-9cf.svg >
11
- <img src=https://img.shields.io/badge/Release-v0.1.0-brightgreen.svg >
11
+ <img src=https://img.shields.io/badge/Release-v0.1.1-brightgreen.svg >
12
12
  </div>
13
13
  <p align="center">
14
14
  DeepCache requires UNet’s U-shape, but DiT lacks it. Most DiT cache accelerators are complex and not training-free. DBCache builds on FBCache to create a training-free, UNet-style cache accelerator for DiT.
@@ -34,7 +34,7 @@
34
34
  |Baseline(L20x1)|F1B0 (0.08)|F1B0 (0.20)|F8B8 (0.15)|F12B12 (0.20)|F16B16 (0.20)|
35
35
  |:---:|:---:|:---:|:---:|:---:|:---:|
36
36
  |24.85s|15.59s|8.58s|15.41s|15.11s|17.74s|
37
- |<img src=https://github.com/vipshop/DBCache/blob/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F1B0S1_R0.08_S11.png width=105px> | <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F1B0S1_R0.2_S19.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F8B8S1_R0.15_S15.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F12B12S4_R0.2_S16.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F16B16S4_R0.2_S13.png width=105px>|
37
+ |<img src=https://github.com/vipshop/DBCache/raw/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F1B0S1_R0.08_S11.png width=105px> | <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F1B0S1_R0.2_S19.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F8B8S1_R0.15_S15.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F12B12S4_R0.2_S16.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F16B16S4_R0.2_S13.png width=105px>|
38
38
  |**Baseline(L20x1)**|**F1B0 (0.08)**|**F8B8 (0.12)**|**F8B12 (0.20)**|**F8B16 (0.20)**|**F8B20 (0.20)**|
39
39
  |27.85s|6.04s|5.88s|5.77s|6.01s|6.20s|
40
40
  |<img src=https://github.com/user-attachments/assets/70ea57f4-d8f2-415b-8a96-d8315974a5e6 width=105px>|<img src=https://github.com/user-attachments/assets/fc0e1a67-19cc-44aa-bf50-04696e7978a0 width=105px> |<img src=https://github.com/user-attachments/assets/d1434896-628c-436b-95ad-43c085a8629e width=105px>|<img src=https://github.com/user-attachments/assets/aaa42cd2-57de-4c4e-8bfb-913018a8251d width=105px>|<img src=https://github.com/user-attachments/assets/dc0ba2a4-ef7c-436d-8a39-67055deab92f width=105px>|<img src=https://github.com/user-attachments/assets/aede466f-61ed-4256-8df0-fecf8020c5ca width=105px>|
@@ -58,7 +58,7 @@ These case studies demonstrate that even with relatively high thresholds (such a
58
58
  |Baseline(L20x1)|Pruned(24%)|Pruned(35%)|Pruned(38%)|Pruned(45%)|Pruned(60%)|
59
59
  |:---:|:---:|:---:|:---:|:---:|:---:|
60
60
  |24.85s|19.43s|16.82s|15.95s|14.24s|10.66s|
61
- |<img src=https://github.com/vipshop/DBCache/blob/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
61
+ |<img src=https://github.com/vipshop/DBCache/raw/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
62
62
 
63
63
  <div align="center">
64
64
  <p align="center">
@@ -235,7 +235,7 @@ apply_cache_on_pipe(pipe, **cache_options)
235
235
  |Baseline(L20x1)|Pruned(24%)|Pruned(35%)|Pruned(38%)|Pruned(45%)|Pruned(60%)|
236
236
  |:---:|:---:|:---:|:---:|:---:|:---:|
237
237
  |24.85s|19.43s|16.82s|15.95s|14.24s|10.66s|
238
- |<img src=https://github.com/vipshop/DBCache/blob/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
238
+ |<img src=https://github.com/vipshop/DBCache/raw/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
239
239
 
240
240
  ## 🎉Context Parallelism
241
241
 
@@ -298,9 +298,9 @@ Otherwise, the recompile_limit error may be triggered, causing the module to fal
298
298
 
299
299
  <div id="supported"></div>
300
300
 
301
- - [🚀FLUX.1](https://github.com/vipshop/DBCache/blob/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
302
- - [🚀CogVideoX](https://github.com/vipshop/DBCache/blob/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
303
- - [🚀Mochi](https://github.com/vipshop/DBCache/blob/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
301
+ - [🚀FLUX.1](https://github.com/vipshop/DBCache/raw/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
302
+ - [🚀CogVideoX](https://github.com/vipshop/DBCache/raw/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
303
+ - [🚀Mochi](https://github.com/vipshop/DBCache/raw/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
304
304
 
305
305
  ## 👋Contribute
306
306
  <div id="contribute"></div>
{cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/_version.py RENAMED
@@ -17,5 +17,5 @@ __version__: str
17
17
  __version_tuple__: VERSION_TUPLE
18
18
  version_tuple: VERSION_TUPLE
19
19
 
20
- __version__ = version = '0.1.0'
21
- __version_tuple__ = version_tuple = (0, 1, 0)
20
+ __version__ = version = '0.1.1'
21
+ __version_tuple__ = version_tuple = (0, 1, 1)
{cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit/cache_factory/__init__.py RENAMED
@@ -160,7 +160,9 @@ def apply_cache_on_pipe(pipe: DiffusionPipeline, *args, **kwargs):
160
160
  elif cache_type == CacheType.DBPrune:
161
161
  return apply_db_prune_on_pipe(pipe, *args, **kwargs)
162
162
  elif cache_type == CacheType.NONE:
163
- logger.warning("Cache type is NONE, no caching will be applied.")
163
+ logger.warning(
164
+ f"Cache type is {cache_type}, no caching will be applied."
165
+ )
164
166
  return pipe
165
167
  else:
166
168
  raise ValueError(f"Unknown cache type: {cache_type}")
{cache_dit-0.1.0 → cache_dit-0.1.1}/src/cache_dit.egg-info/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: cache_dit
3
- Version: 0.1.0
3
+ Version: 0.1.1
4
4
  Summary: ⚡️DBCache: A Training-free UNet-style Cache Acceleration for Diffusion Transformers
5
5
  Author: DefTruth, vipshop.com, etc.
6
6
  Maintainer: DefTruth, vipshop.com, etc
@@ -37,13 +37,13 @@ Dynamic: requires-python
37
37
  <p align="center">
38
38
  <h3>⚡️DBCache: A Training-free UNet-style Cache Acceleration for <br>Diffusion Transformers</h2>
39
39
  </p>
40
- <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCache.png >
40
+ <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCache.png >
41
41
  <div align='center'>
42
42
  <img src=https://img.shields.io/badge/Language-Python-brightgreen.svg >
43
43
  <img src=https://img.shields.io/badge/PRs-welcome-9cf.svg >
44
- <img src=https://img.shields.io/badge/Build-pass-brightgreen.svg >
44
+ <img src=https://img.shields.io/badge/PyPI-pass-brightgreen.svg >
45
45
  <img src=https://img.shields.io/badge/Python-3.10|3.11|3.12-9cf.svg >
46
- <img src=https://img.shields.io/badge/Release-v0.1.0-brightgreen.svg >
46
+ <img src=https://img.shields.io/badge/Release-v0.1.1-brightgreen.svg >
47
47
  </div>
48
48
  <p align="center">
49
49
  DeepCache requires UNet’s U-shape, but DiT lacks it. Most DiT cache accelerators are complex and not training-free. DBCache builds on FBCache to create a training-free, UNet-style cache accelerator for DiT.
@@ -69,7 +69,7 @@ Dynamic: requires-python
69
69
  |Baseline(L20x1)|F1B0 (0.08)|F1B0 (0.20)|F8B8 (0.15)|F12B12 (0.20)|F16B16 (0.20)|
70
70
  |:---:|:---:|:---:|:---:|:---:|:---:|
71
71
  |24.85s|15.59s|8.58s|15.41s|15.11s|17.74s|
72
- |<img src=https://github.com/vipshop/DBCache/blob/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F1B0S1_R0.08_S11.png width=105px> | <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F1B0S1_R0.2_S19.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F8B8S1_R0.15_S15.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F12B12S4_R0.2_S16.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBCACHE_F16B16S4_R0.2_S13.png width=105px>|
72
+ |<img src=https://github.com/vipshop/DBCache/raw/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F1B0S1_R0.08_S11.png width=105px> | <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F1B0S1_R0.2_S19.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F8B8S1_R0.15_S15.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F12B12S4_R0.2_S16.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBCACHE_F16B16S4_R0.2_S13.png width=105px>|
73
73
  |**Baseline(L20x1)**|**F1B0 (0.08)**|**F8B8 (0.12)**|**F8B12 (0.20)**|**F8B16 (0.20)**|**F8B20 (0.20)**|
74
74
  |27.85s|6.04s|5.88s|5.77s|6.01s|6.20s|
75
75
  |<img src=https://github.com/user-attachments/assets/70ea57f4-d8f2-415b-8a96-d8315974a5e6 width=105px>|<img src=https://github.com/user-attachments/assets/fc0e1a67-19cc-44aa-bf50-04696e7978a0 width=105px> |<img src=https://github.com/user-attachments/assets/d1434896-628c-436b-95ad-43c085a8629e width=105px>|<img src=https://github.com/user-attachments/assets/aaa42cd2-57de-4c4e-8bfb-913018a8251d width=105px>|<img src=https://github.com/user-attachments/assets/dc0ba2a4-ef7c-436d-8a39-67055deab92f width=105px>|<img src=https://github.com/user-attachments/assets/aede466f-61ed-4256-8df0-fecf8020c5ca width=105px>|
@@ -93,7 +93,7 @@ These case studies demonstrate that even with relatively high thresholds (such a
93
93
  |Baseline(L20x1)|Pruned(24%)|Pruned(35%)|Pruned(38%)|Pruned(45%)|Pruned(60%)|
94
94
  |:---:|:---:|:---:|:---:|:---:|:---:|
95
95
  |24.85s|19.43s|16.82s|15.95s|14.24s|10.66s|
96
- |<img src=https://github.com/vipshop/DBCache/blob/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
96
+ |<img src=https://github.com/vipshop/DBCache/raw/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
97
97
 
98
98
  <div align="center">
99
99
  <p align="center">
@@ -270,7 +270,7 @@ apply_cache_on_pipe(pipe, **cache_options)
270
270
  |Baseline(L20x1)|Pruned(24%)|Pruned(35%)|Pruned(38%)|Pruned(45%)|Pruned(60%)|
271
271
  |:---:|:---:|:---:|:---:|:---:|:---:|
272
272
  |24.85s|19.43s|16.82s|15.95s|14.24s|10.66s|
273
- |<img src=https://github.com/vipshop/DBCache/blob/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/blob/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
273
+ |<img src=https://github.com/vipshop/DBCache/raw/main/assets/NONE_R0.08_S0.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.03_P24.0_T19.43s.png width=105px> | <img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.04_P34.6_T16.82s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.05_P38.3_T15.95s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.06_P45.2_T14.24s.png width=105px>|<img src=https://github.com/vipshop/DBCache/raw/main/assets/DBPRUNE_F1B0_R0.2_P59.5_T10.66s.png width=105px>|
274
274
 
275
275
  ## 🎉Context Parallelism
276
276
 
@@ -333,9 +333,9 @@ Otherwise, the recompile_limit error may be triggered, causing the module to fal
333
333
 
334
334
  <div id="supported"></div>
335
335
 
336
- - [🚀FLUX.1](https://github.com/vipshop/DBCache/blob/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
337
- - [🚀CogVideoX](https://github.com/vipshop/DBCache/blob/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
338
- - [🚀Mochi](https://github.com/vipshop/DBCache/blob/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
336
+ - [🚀FLUX.1](https://github.com/vipshop/DBCache/raw/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
337
+ - [🚀CogVideoX](https://github.com/vipshop/DBCache/raw/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
338
+ - [🚀Mochi](https://github.com/vipshop/DBCache/raw/main/src/cache_dit/cache_factory/dual_block_cache/diffusers_adapters)
339
339
 
340
340
  ## 👋Contribute
341
341
  <div id="contribute"></div>
{cache_dit-0.1.0 → cache_dit-0.1.1}/.gitignore RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/CONTRIBUTE.md RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/LICENSE RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/MANIFEST.in RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/assets/DBCache.png RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/bench/.gitignore RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/bench/bench.py RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/docs/.gitignore RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/examples/.gitignore RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/pyproject.toml RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/pytest.ini RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/requirements.txt RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/setup.cfg RENAMED
File without changes
{cache_dit-0.1.0 → cache_dit-0.1.1}/setup.py RENAMED
File without changes