cache-dit 0.2.34__py3-none-any.whl → 0.2.36__py3-none-any.whl

cache_dit/utils.py

@@ -1,6 +1,9 @@
 import torch
 import dataclasses
 import diffusers
+import builtins as __builtin__
+import contextlib
+
 import numpy as np
 from pprint import pprint
 from diffusers import DiffusionPipeline
@@ -13,6 +16,18 @@ from cache_dit.logger import init_logger
 logger = init_logger(__name__)
 
 
+def dummy_print(*args, **kwargs):
+    pass
+
+
+@contextlib.contextmanager
+def disable_print():
+    origin_print = __builtin__.print
+    __builtin__.print = dummy_print
+    yield
+    __builtin__.print = origin_print
+
+
 @torch.compiler.disable
 def is_diffusers_at_least_0_3_5() -> bool:
     return diffusers.__version__ >= "0.35.0"

{cache_dit-0.2.34.dist-info → cache_dit-0.2.36.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cache_dit
-Version: 0.2.34
+Version: 0.2.36
 Summary: 🤗 A Unified and Training-free Cache Acceleration Toolbox for Diffusion Transformers
 Author: DefTruth, vipshop.com, etc.
 Maintainer: DefTruth, vipshop.com, etc
@@ -18,7 +18,12 @@ Requires-Dist: scikit-image
 Requires-Dist: scipy
 Requires-Dist: lpips==0.1.4
 Requires-Dist: torchao>=0.12.0
+Requires-Dist: image-reward
 Provides-Extra: all
+Provides-Extra: metrics
+Requires-Dist: image-reward; extra == "metrics"
+Requires-Dist: pytorch-fid; extra == "metrics"
+Requires-Dist: lpips==0.1.4; extra == "metrics"
 Provides-Extra: dev
 Requires-Dist: pre-commit; extra == "dev"
 Requires-Dist: pytest<8.0.0,>=7.0.0; extra == "dev"
@@ -56,7 +61,8 @@ Dynamic: requires-python
       <img src=https://img.shields.io/badge/Release-v0.2-brightgreen.svg >
  </div>
   <p align="center">
-  🔥<b><a href="#unified">Unified Cache APIs</a> | <a href="#dbcache">DBCache</a> | <a href="#taylorseer">Hybrid TaylorSeer</a> | <a href="#cfg">Hybrid Cache CFG</a></b>🔥
+    <b><a href="#unified">📚Unified Cache APIs</a></b> | <a href="#forward-pattern-matching">📚Forward Pattern Matching</a> | <a href="#automatic-block-adapter">📚Automatic Block Adapter</a><br>
+    <a href="#hybird-forward-pattern">📚Hybrid Forward Pattern</a> | <a href="#dbcache">📚DBCache</a> | <a href="#taylorseer">📚Hybrid TaylorSeer</a> | <a href="#cfg">📚Cache CFG</a>
   </p>
   <p align="center">
     🎉Now, <b>cache-dit</b> covers <b>most</b> mainstream Diffusers' <b>DiT</b> Pipelines🎉<br>
@@ -111,8 +117,8 @@ Dynamic: requires-python
   <img src=https://github.com/vipshop/cache-dit/raw/main/assets/gifs/skyreels_v2.C0_L0_Q0_NONE.gif width=125px>
   <img src=https://github.com/vipshop/cache-dit/raw/main/assets/gifs/skyreels_v2.C0_L0_Q0_DBCACHE_F8B0_W8M0MC0_T0O2_R0.12_S17.gif width=125px>
   <p><b>🔥Mochi-1-preview</b> | <a href="https://github.com/vipshop/cache-dit">+cache-dit</a>:1.8x↑🎉 | <b>SkyReelsV2</b> | <a href="https://github.com/vipshop/cache-dit">+cache-dit</a>:1.6x↑🎉</p>
-  <img src=./examples/data/visualcloze/00555_00.jpg width=100px>
-  <img src=./examples/data/visualcloze/12265_00.jpg width=100px>
+  <img src=https://github.com/vipshop/cache-dit/raw/main/examples/data/visualcloze/00555_00.jpg width=100px>
+  <img src=https://github.com/vipshop/cache-dit/raw/main/examples/data/visualcloze/12265_00.jpg width=100px>
   <img src=https://github.com/vipshop/cache-dit/raw/main/assets/visualcloze-512.C0_L0_Q0_NONE.png width=100px>
   <img src=https://github.com/vipshop/cache-dit/raw/main/assets/visualcloze-512.C0_L0_Q0_DBCACHE_F8B0_W8M0MC0_T0O2_R0.08_S15.png width=100px>
   <img src=https://github.com/vipshop/cache-dit/raw/main/assets/visualcloze-512.C0_L0_Q0_DBCACHE_F1B0_W8M0MC0_T0O2_R0.08_S18.png width=100px>
@@ -180,14 +186,15 @@ Dynamic: requires-python
 <div id="contents"></div>  
 
 - [⚙️Installation](#️installation)
-- [🔥Supported Models](#supported)
+- [🔥Benchmarks](#benchmarks)
+- [🔥Supported Pipelines](#supported)
 - [🎉Unified Cache APIs](#unified)
-  - [📚Forward Pattern Matching](#unified)
-  - [♥️Cache with One-line Code](#unified)
-  - [🔥Automatic Block Adapter](#unified)
-  - [📚Hybird Forward Pattern](#unified)
-  - [📚Implement Patch Functor](#unified)
-  - [🤖Cache Acceleration Stats](#unified)
+  - [📚Forward Pattern Matching](#forward-pattern-matching)
+  - [♥️Cache with One-line Code](#%EF%B8%8Fcache-acceleration-with-one-line-code)
+  - [🔥Automatic Block Adapter](#automatic-block-adapter)
+  - [📚Hybird Forward Pattern](#automatic-block-adapter)
+  - [📚Implement Patch Functor](#implement-patch-functor)
+  - [🤖Cache Acceleration Stats](#cache-acceleration-stats-summary)
 - [⚡️Dual Block Cache](#dbcache)
 - [🔥Hybrid TaylorSeer](#taylorseer)
 - [⚡️Hybrid Cache CFG](#cfg)
@@ -209,36 +216,48 @@ Or you can install the latest develop version from GitHub:
 pip3 install git+https://github.com/vipshop/cache-dit.git
 ```
 
-## 🔥Supported Models  
+## 🔥Supported Pipelines  
 
 <div id="supported"></div>
 
-Currently, **cache-dit** library supports almost **Any** Diffusion Transformers (with **Transformer Blocks** that match the specific Input and Output **patterns**). Please check [🎉Unified Cache APIs](#unified) for more details. Here are just some of the tested models listed:
+Currently, **cache-dit** library supports almost **Any** Diffusion Transformers (with **Transformer Blocks** that match the specific Input and Output **patterns**). Please check [🎉Examples](./examples/pipeline) for more details. Here are just some of the tested models listed.
+
+```python
+>>> import cache_dit
+>>> cache_dit.supported_pipelines()
+(30, ['Flux*', 'Mochi*', 'CogVideoX*', 'Wan*', 'HunyuanVideo*', 'QwenImage*', 'LTX*', 'Allegro*',
+'CogView3Plus*', 'CogView4*', 'Cosmos*', 'EasyAnimate*', 'SkyReelsV2*', 'StableDiffusion3*',
+'ConsisID*', 'DiT*', 'Amused*', 'Bria*', 'Lumina*', 'OmniGen*', 'PixArt*', 'Sana*', 'StableAudio*',
+'VisualCloze*', 'AuraFlow*', 'Chroma*', 'ShapE*', 'HiDream*', 'HunyuanDiT*', 'HunyuanDiTPAG*'])
+```
+
+<details>
+<summary> Show all pipelines </summary>  
 
 - [🚀HunyuanImage-2.1](https://github.com/vipshop/cache-dit/raw/main/examples)  
-- [🚀Qwen-Image-Lightning](https://github.com/vipshop/cache-dit/raw/main/examples)  
+- [🚀Qwen-Image-Lightning](https://github.com/vipshop/cache-dit/raw/main/examples)
 - [🚀Qwen-Image-Edit](https://github.com/vipshop/cache-dit/raw/main/examples)  
 - [🚀Qwen-Image](https://github.com/vipshop/cache-dit/raw/main/examples)  
-- [🚀SkyReelsV2](https://github.com/vipshop/cache-dit/raw/main/examples)  
-- [🚀LTXVideo](https://github.com/vipshop/cache-dit/raw/main/examples)  
-- [🚀OmniGen](https://github.com/vipshop/cache-dit/raw/main/examples)  
-- [🚀Lumina2](https://github.com/vipshop/cache-dit/raw/main/examples)  
 - [🚀FLUX.1-dev](https://github.com/vipshop/cache-dit/raw/main/examples)  
 - [🚀FLUX.1-Fill-dev](https://github.com/vipshop/cache-dit/raw/main/examples)  
-- [🚀FLUX.1-Kontext-dev](https://github.com/vipshop/cache-dit/raw/main/examples)  
-- [🚀Chroma1-HD](https://github.com/vipshop/cache-dit/raw/main/examples)  
-- [🚀VisualCloze](https://github.com/vipshop/cache-dit/raw/main/examples)  
-- [🚀CogVideoX](https://github.com/vipshop/cache-dit/raw/main/examples)
-- [🚀CogVideoX1.5](https://github.com/vipshop/cache-dit/raw/main/examples)
-- [🚀CogView3-Plus](https://github.com/vipshop/cache-dit/raw/main/examples)
+- [🚀FLUX.1-Kontext-dev](https://github.com/vipshop/cache-dit/raw/main/examples)
 - [🚀CogView4](https://github.com/vipshop/cache-dit/raw/main/examples)
 - [🚀Wan2.2-T2V](https://github.com/vipshop/cache-dit/raw/main/examples)
+- [🚀HunyuanVideo](https://github.com/vipshop/cache-dit/raw/main/examples)
+- [🚀HiDream-I1-Full](https://github.com/vipshop/cache-dit/raw/main/examples)
+- [🚀HunyuanDiT](https://github.com/vipshop/cache-dit/raw/main/examples)
 - [🚀Wan2.1-T2V](https://github.com/vipshop/cache-dit/raw/main/examples)
 - [🚀Wan2.1-FLF2V](https://github.com/vipshop/cache-dit/raw/main/examples)
+- [🚀SkyReelsV2](https://github.com/vipshop/cache-dit/raw/main/examples)  
+- [🚀Chroma1-HD](https://github.com/vipshop/cache-dit/raw/main/examples)  
+- [🚀CogVideoX1.5](https://github.com/vipshop/cache-dit/raw/main/examples)
+- [🚀CogView3-Plus](https://github.com/vipshop/cache-dit/raw/main/examples)
+- [🚀CogVideoX](https://github.com/vipshop/cache-dit/raw/main/examples)
+- [🚀VisualCloze](https://github.com/vipshop/cache-dit/raw/main/examples)  
+- [🚀LTXVideo](https://github.com/vipshop/cache-dit/raw/main/examples)  
+- [🚀OmniGen](https://github.com/vipshop/cache-dit/raw/main/examples)  
+- [🚀Lumina2](https://github.com/vipshop/cache-dit/raw/main/examples)  
 - [🚀mochi-1-preview](https://github.com/vipshop/cache-dit/raw/main/examples)
-- [🚀HunyuanVideo](https://github.com/vipshop/cache-dit/raw/main/examples)
-- [🚀HunyuanDiT](https://github.com/vipshop/cache-dit/raw/main/examples)
-- [🚀HiDream-I1-Full](https://github.com/vipshop/cache-dit/raw/main/examples)
 - [🚀AuraFlow-v0.3](https://github.com/vipshop/cache-dit/raw/main/examples)
 - [🚀PixArt-Alpha](https://github.com/vipshop/cache-dit/raw/main/examples)
 - [🚀PixArt-Sigma](https://github.com/vipshop/cache-dit/raw/main/examples)
@@ -252,6 +271,50 @@ Currently, **cache-dit** library supports almost **Any** Diffusion Transformers
 
 </details>
 
+## 🔥Benchmarks
+
+<div id="benchmarks"></div>
+
+Take FLUX.1-dev as an example. Here, only the results of some precision and performance benchmarks are presented. The test dataset is DrawBench. For a complete benchmark, please refer to [benchmarks](./bench/). **Device**: NVIDIA L20. **F**: Fn_compute_blocks, **B**: Bn_compute_blocks.
+
+| Config | Clip Score(↑) | ImageReward(↑) | PSNR(↑) | TFLOPs(↑) | SpeedUp(↑) |
+| --- | --- | --- | --- | --- | --- |
+| [**FLUX.1**-dev]: 50 steps | 32.9217 | 1.0412 | INF | 3726.87 | 1.00 |
+| F8B0_W8MC0_R0.08 | 33.0070 | 1.0333 | 35.2008 | 2162.19 | 1.72x |
+| F8B0_W4MC0_R0.08 | 32.9871 | 1.0370 | 33.8317 | 2064.81 | 1.80x |
+| F4B0_W4MC2_R0.12 | 32.9718 | 1.0301 | 31.9394 | 1678.98 | 2.22x |
+| F8B0_W8MC3_R0.12 | 32.9613 | 1.0270 | 34.2834 | 1977.69 | 1.88x |
+| F8B0_W4MC2_R0.12 | 32.9535 | 1.0185 | 32.7346 | 1935.73 | 1.93x |
+| F8B0_W8MC2_R0.12 | 32.9302 | 1.0227 | 34.7449 | 2072.18 | 1.80x |
+| F8B0_W4MC3_R0.12 | 32.9234 | 1.0085 | 32.5385 | 1816.58 | 2.05x |
+| F8B0_W8MC4_R0.12 | 32.9041 | 1.0140 | 33.9466 | 1897.61 | 1.96x |
+| F4B0_W4MC3_R0.12 | 32.8981 | 1.0130 | 31.8031 | 1507.83 | 2.47x |
+| F4B0_W4MC0_R0.08 | 32.8544 | 1.0065 | 32.3555 | 1654.72 | 2.25x |
+| F8B0_W4MC4_R0.12 | 32.8443 | 1.0102 | 32.4231 | 1753.48 | 2.13x |
+| F4B0_W4MC4_R0.12 | 32.8384 | 1.0065 | 31.5292 | 1400.08 | 2.66x |
+| F1B0_W4MC4_R0.12 | 32.8291 | 1.0181 | 32.9462 | 1401.61 | 2.66x |
+| F1B0_W4MC3_R0.12 | 32.8236 | 1.0166 | 33.0037 | 1457.62 | 2.56x |
+
+The comparison between DBCache and algorithms such as Δ-DiT, Chipmunk, FORA, DuCa, TaylorSeer and FoCa is as follows. Now, in the comparison with a speedup ratio less than **3x**, cache-dit achieved the best accuracy. Please check [📚How to Reproduce?](./bench/) for more details.
+
+| Method | TFLOPs(↓) | SpeedUp(↑) | ImageReward(↑) | Clip Score(↑) |
+| --- | --- | --- | --- | --- |
+| [**FLUX.1**-dev]: 50 steps | 3726.87 | 1.00× | 0.9898 | 32.404 |
+| [**FLUX.1**-dev]: 60% steps | 2231.70 | 1.67× | 0.9663 | 32.312 |
+| Δ-DiT (N=2) | 2480.01 | 1.50× | 0.9444 | 32.273 |
+| Δ-DiT (N=3) | 1686.76 | 2.21× | 0.8721 | 32.102 |
+| [**FLUX.1**-dev]: 34% steps | 1264.63 | 3.13× | 0.9453 | 32.114 |
+| Chipmunk | 1505.87 | 2.47× | 0.9936 | 32.776 |
+| FORA (N=3) | 1320.07 | 2.82× | 0.9776 | 32.266 |
+| **[DBCache (F=4, B=0)](https://github.com/vipshop/cache-dit)** | **1400.08** | **2.66×** | **1.0065** | **32.838** |
+| **[DBCache + TaylorSeer (F=4, B=0)](https://github.com/vipshop/cache-dit)** | **1388.30** | **2.68×** | **1.0287** | **32.914** |
+| DuCa(N=5) | 978.76 | 3.80× | 0.9955 | 32.241 |
+| TaylorSeer (N=4, O=2) | 1042.27 | 3.57× | 0.9857 | 32.413 |
+| **[FoCa (N=5) arxiv.2508.16211](https://arxiv.org/pdf/2508.16211)** | **893.54** | **4.16×** | **1.0029** | **32.948** |
+
+cache-dit will support more mainstream Cache acceleration algorithms in the future. More benchmarks will be released, please stay tuned for update. 
+
+
 ## 🎉Unified Cache APIs
 
 <div id="unified"></div>  
@@ -563,13 +626,19 @@ You can utilize the APIs provided by cache-dit to quickly evaluate the accuracy
 
 ```python
 from cache_dit.metrics import compute_psnr
-from cache_dit.metrics import compute_video_psnr
-from cache_dit.metrics import FrechetInceptionDistance  # FID
-
-FID = FrechetInceptionDistance()
-image_psnr, n = compute_psnr("true.png", "test.png") # Num: n
-image_fid,  n = FID.compute_fid("true_dir", "test_dir")
-video_psnr, n = compute_video_psnr("true.mp4", "test.mp4") # Frames: n
+from cache_dit.metrics import compute_ssim
+from cache_dit.metrics import compute_fid
+from cache_dit.metrics import compute_lpips
+from cache_dit.metrics import compute_clip_score
+from cache_dit.metrics import compute_image_reward
+
+psnr,       n = compute_psnr("true.png", "test.png") # Num: n
+psnr,       n = compute_psnr("true_dir", "test_dir")
+ssim,       n = compute_ssim("true_dir", "test_dir")
+fid,        n = compute_fid("true_dir", "test_dir")
+lpips,      n = compute_lpips("true_dir", "test_dir")
+clip_score, n = compute_clip_score("DrawBench200.txt", "test_dir")
+reward,     n = compute_image_reward("DrawBench200.txt", "test_dir")
 ```
 
 Please check [test_metrics.py](./tests/test_metrics.py) for more details. Or, you can use `cache-dit-metrics-cli` tool. For examples: 

{cache_dit-0.2.34.dist-info → cache_dit-0.2.36.dist-info}/RECORD

@@ -1,7 +1,7 @@
-cache_dit/__init__.py,sha256=kX9V-FegZG4c8LMwI4PTmMqH794MEW0pzDArdhC0cJw,1241
-cache_dit/_version.py,sha256=CtkelOzOJFXtgJ0APT8pLd5zWrG63eLavWaOD_cX7xo,706
+cache_dit/__init__.py,sha256=hzaexC1VQ0TxiWY6TJ1lTm-04e65WOTNHOfYryu1vFA,1284
+cache_dit/_version.py,sha256=y3W4kIzeljZ6sUAtO8hW9y1LA6HKsN9jWHCm6JjF5gw,706
 cache_dit/logger.py,sha256=0zsu42hN-3-rgGC_C29ms1IvVpV4_b4_SwJCKSenxBE,4304
-cache_dit/utils.py,sha256=WK7eqgH6gCYNHXNLmWyxBDU0XSHTPg7CfOcyXlGXBqE,10510
+cache_dit/utils.py,sha256=nuHHr6NB286qE9u6klLNfhAVRMOGipihOhM8LRqznmU,10775
 cache_dit/cache_factory/.gitignore,sha256=5Cb-qT9wsTUoMJ7vACDF7ZcLpAXhi5v-xdcWSRit988,23
 cache_dit/cache_factory/__init__.py,sha256=Iw6-iJLFbdzCsIDZXXOw371L-HPmoeZO_P9a3sDjP5s,1103
 cache_dit/cache_factory/cache_adapters.py,sha256=OFJlxxyODhoZstN4EfPgC7tE8M1ZdQFcE25gDNrW7NA,18212
@@ -33,17 +33,19 @@ cache_dit/compile/utils.py,sha256=nN2OIrSdwRR5zGxJinKDqb07pXpvTNTF3g_OgLkeeBU,38
 cache_dit/custom_ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cache_dit/custom_ops/triton_taylorseer.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cache_dit/metrics/__init__.py,sha256=RaUhl5dieF40RqnizGzR30qoJJ9dyMUEADwgwMaMQrE,575
+cache_dit/metrics/clip_score.py,sha256=ERNCFQFJKzJdbIX9OAg-1LiSPuXUVHLOFxbf2gcENpc,3938
 cache_dit/metrics/config.py,sha256=ieOgD9ayz722RjVzk24bSIqS2D6o7TZjGk8KeXV-OLQ,551
-cache_dit/metrics/fid.py,sha256=9Ivtazl6mW0Bon2VXa-Ia5Xj2ewxRD3V1Qkd69zYM3Y,17066
+cache_dit/metrics/fid.py,sha256=ZM_FM0XERtpnkMUfphmw2aOdljrh1uba-pnYItu0q6M,18219
+cache_dit/metrics/image_reward.py,sha256=N8HalJo1T1js0dsNb2V1KRv4kIdcm3nhx7iOXJuqcns,5421
 cache_dit/metrics/inception.py,sha256=pBVe2X6ylLPIXTG4-GWDM9DWnCviMJbJ45R3ulhktR0,12759
-cache_dit/metrics/lpips.py,sha256=I2qCNi6qJh5TRsaIsdxO0WoRX1DN7U_H3zS0oCSahYM,1032
-cache_dit/metrics/metrics.py,sha256=8jvM1sF-nDxUuwCRy44QEoo4dYVLCQVh1QyAMs4eaQY,27840
+cache_dit/metrics/lpips.py,sha256=hrHrmdM-f2B4TKDs0xLqJO5JFaYcCjq2qNIR8oCrVkc,811
+cache_dit/metrics/metrics.py,sha256=RADSUUMYKBMkABsYFCEr_9PV8cDXLuxe2xuQ-mRBs4Y,39691
 cache_dit/quantize/__init__.py,sha256=kWYoMAyZgBXu9BJlZjTQ0dRffW9GqeeY9_iTkXrb70A,59
 cache_dit/quantize/quantize_ao.py,sha256=Fx1KW4l3gdEkdrcAYtPoDW7WKBJWrs3glOHiEwW_TgE,6160
 cache_dit/quantize/quantize_interface.py,sha256=2s_R7xPSKuJeFpEGeLwRxnq_CqJcBG3a3lzyW5wh-UM,1241
-cache_dit-0.2.34.dist-info/licenses/LICENSE,sha256=Dqb07Ik2dV41s9nIdMUbiRWEfDqo7-dQeRiY7kPO8PE,3769
-cache_dit-0.2.34.dist-info/METADATA,sha256=BvEY08xjrGPcqTEZSHvSDtJP4sGZv1T6jzhGj-jQbvo,38284
-cache_dit-0.2.34.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-cache_dit-0.2.34.dist-info/entry_points.txt,sha256=FX2gysXaZx6NeK1iCLMcIdP8Q4_qikkIHtEmi3oWn8o,65
-cache_dit-0.2.34.dist-info/top_level.txt,sha256=ZJDydonLEhujzz0FOkVbO-BqfzO9d_VqRHmZU-3MOZo,10
-cache_dit-0.2.34.dist-info/RECORD,,
+cache_dit-0.2.36.dist-info/licenses/LICENSE,sha256=Dqb07Ik2dV41s9nIdMUbiRWEfDqo7-dQeRiY7kPO8PE,3769
+cache_dit-0.2.36.dist-info/METADATA,sha256=2WIwYYezSUUk0rnIutttA2-s6_yTSCz1BwiAfO9cbQI,42706
+cache_dit-0.2.36.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cache_dit-0.2.36.dist-info/entry_points.txt,sha256=FX2gysXaZx6NeK1iCLMcIdP8Q4_qikkIHtEmi3oWn8o,65
+cache_dit-0.2.36.dist-info/top_level.txt,sha256=ZJDydonLEhujzz0FOkVbO-BqfzO9d_VqRHmZU-3MOZo,10
+cache_dit-0.2.36.dist-info/RECORD,,