cache-dit 0.2.21__py3-none-any.whl → 0.2.23__py3-none-any.whl

{cache_dit-0.2.21.dist-info → cache_dit-0.2.23.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cache_dit
-Version: 0.2.21
+Version: 0.2.23
 Summary: 🤗 CacheDiT: An Unified and Training-free Cache Acceleration Toolbox for Diffusion Transformers
 Author: DefTruth, vipshop.com, etc.
 Maintainer: DefTruth, vipshop.com, etc
@@ -173,17 +173,23 @@ But in some cases, you may have a **modified** Diffusion Pipeline or Transformer
 ```python
 from cache_dit import ForwardPattern, BlockAdapter
 
-# Please check docs/BlockAdapter.md for more details.
+# Use BlockAdapter with `auto` mode.
+cache_dit.enable_cache(
+    BlockAdapter(pipe=pipe, auto=True), # Qwen-Image, etc.  
+    # Check `📚Forward Pattern Matching` documentation and hack the code of
+    # of Qwen-Image, you will find that it has satisfied `FORWARD_PATTERN_1`.
+    forward_pattern=ForwardPattern.Pattern_1,  
+)
+
+# Or, manualy setup transformer configurations.
 cache_dit.enable_cache(
     BlockAdapter(
         pipe=pipe, # Qwen-Image, etc.
         transformer=pipe.transformer,
         blocks=pipe.transformer.transformer_blocks,
         blocks_name="transformer_blocks",
-    ),  
-    # Check `📚Forward Pattern Matching` documentation and hack the code of
-    # of Qwen-Image, you will find that it has satisfied `FORWARD_PATTERN_1`.
-    forward_pattern=ForwardPattern.Pattern_1,  
+    ), 
+    forward_pattern=ForwardPattern.Pattern_1,
 )
 ```
 For such situations, **BlockAdapter** can help you quickly apply various cache acceleration features to your own Diffusion Pipelines and Transformers. Please check the [📚BlockAdapter.md](./docs/BlockAdapter.md) for more details.
@@ -200,7 +206,7 @@ You can set `details` param as `True` to show more details of cache stats. (mark
 ```python
 ⚡️Cache Steps and Residual Diffs Statistics: QwenImagePipeline
 
-| Cache Steps | Diffs P00 | Diffs P25 | Diffs P50 | Diffs P75 | Diffs P95 | Diffs Max |
+| Cache Steps | Diffs Min | Diffs P25 | Diffs P50 | Diffs P75 | Diffs P95 | Diffs Max |
 |-------------|-----------|-----------|-----------|-----------|-----------|-----------|
 | 23          | 0.045     | 0.084     | 0.114     | 0.147     | 0.241     | 0.297     |
 ```
@@ -209,7 +215,7 @@ You can set `details` param as `True` to show more details of cache stats. (mark
 
 <div id="dbcache"></div>
 
-![](https://github.com/vipshop/cache-dit/raw/main/assets/dbcache-fnbn-v1.png)
+![](https://github.com/vipshop/cache-dit/raw/main/assets/dbcache-v1.png)
 
 **DBCache**: **Dual Block Caching** for Diffusion Transformers. Different configurations of compute blocks (**F8B12**, etc.) can be customized in DBCache, enabling a balanced trade-off between performance and precision. Moreover, it can be entirely **training**-**free**. Please check [DBCache.md](./docs/DBCache.md) docs for more design details.
 
@@ -314,7 +320,7 @@ cache_dit.enable_cache(
 
 <div id="cfg"></div>
 
-cache-dit supports caching for **CFG (classifier-free guidance)**. For models that fuse CFG and non-CFG into a single forward step, or models that do not include CFG (classifier-free guidance) in the forward step, please set `do_separate_classifier_free_guidance` param to **False (default)**. Otherwise, set it to True. For examples:
+cache-dit supports caching for **CFG (classifier-free guidance)**. For models that fuse CFG and non-CFG into a single forward step, or models that do not include CFG (classifier-free guidance) in the forward step, please set `do_separate_cfg` param to **False (default)**. Otherwise, set it to True. For examples:
 
 ```python
 cache_dit.enable_cache(
@@ -322,10 +328,10 @@ cache_dit.enable_cache(
     ...,
     # CFG: classifier free guidance or not
     # For model that fused CFG and non-CFG into single forward step,
-    # should set do_separate_classifier_free_guidance as False.
-    # For example, set it as True for Wan 2.1 and set it as False 
-    # for FLUX.1, HunyuanVideo, CogVideoX, Mochi.
-    do_separate_classifier_free_guidance=True, # Wan 2.1, Qwen-Image
+    # should set do_separate_cfg as False. For example, set it as True 
+    # for Wan 2.1/Qwen-Image and set it as False for FLUX.1, HunyuanVideo, 
+    # CogVideoX, Mochi, etc.
+    do_separate_cfg=True, # Wan 2.1, Qwen-Image
     # Compute cfg forward first or not, default False, namely, 
     # 0, 2, 4, ..., -> non-CFG step; 1, 3, 5, ... -> CFG step.
     cfg_compute_first=False,
@@ -381,10 +387,6 @@ cache-dit-metrics-cli -h  # show usage
 # all: PSNR, FID, SSIM, MSE, ..., etc.
 cache-dit-metrics-cli all  -i1 true.png -i2 test.png  # image
 cache-dit-metrics-cli all  -i1 true_dir -i2 test_dir  # image dir
-cache-dit-metrics-cli all  -v1 true.mp4 -v2 test.mp4  # video
-cache-dit-metrics-cli all  -v1 true_dir -v2 test_dir  # video dir
-cache-dit-metrics-cli fid  -i1 true_dir -i2 test_dir  # FID
-cache-dit-metrics-cli psnr -i1 true_dir -i2 test_dir  # PSNR
 ```
 
 ## 👋Contribute 

cache_dit-0.2.23.dist-info/RECORD

@@ -0,0 +1,33 @@
+cache_dit/__init__.py,sha256=KwhX9NfYkWSvDFuuUVeVjcuiZiGS_22y386l8j4afMo,905
+cache_dit/_version.py,sha256=6GZdGbiFdhndXqR5oFLOd8VGzUvRkESP-NyStAZWYUw,706
+cache_dit/logger.py,sha256=0zsu42hN-3-rgGC_C29ms1IvVpV4_b4_SwJCKSenxBE,4304
+cache_dit/primitives.py,sha256=A2iG9YLot3gOsZSPp-_gyjqjLgJvWQRx8aitD4JQ23Y,3877
+cache_dit/utils.py,sha256=3UgVhfmTFG28w6CV-Rfxp5u1uzLrRozocHwLCTGiQ5M,5865
+cache_dit/cache_factory/.gitignore,sha256=5Cb-qT9wsTUoMJ7vACDF7ZcLpAXhi5v-xdcWSRit988,23
+cache_dit/cache_factory/__init__.py,sha256=evWenCin1kuBGa6W5BCKMrDZc1C1R2uVPSg0BjXgdXE,499
+cache_dit/cache_factory/cache_adapters.py,sha256=QTSwjdCmHDeF80TLp6D3KhzQS_oMPna0_bESgJBrdkg,23978
+cache_dit/cache_factory/cache_blocks.py,sha256=ZeazBsYvLIjI5M_OnLL2xP2W7zMeM0rxVfBBwIVHBRs,18661
+cache_dit/cache_factory/cache_context.py,sha256=4thx9NYxVaYZ_Nr2quUVE8bsNmTsXhZK0F960rccOc8,39000
+cache_dit/cache_factory/cache_interface.py,sha256=PohG_2oy747O37YSsWz_DwxxTXN7ORhQatyEbg_6fQs,8045
+cache_dit/cache_factory/cache_types.py,sha256=FIFa6ZBfvvSMMHyBBhvarvgg2Y2wbRgITcG_uGylGe0,991
+cache_dit/cache_factory/forward_pattern.py,sha256=B2YeqV2t_zo2Ar8m7qimPBjwQgoXHGp2grPZmEAhi8s,1286
+cache_dit/cache_factory/taylorseer.py,sha256=WeK2WlAJa4Px_pnAKokmnZXeqQYylQkPw4-EDqBIqeQ,3770
+cache_dit/cache_factory/utils.py,sha256=YGtn02O3fVlrfQ32gGV4WAtTRvzzwSXNxzP_FmnE2Uk,1867
+cache_dit/cache_factory/patch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+cache_dit/cache_factory/patch/flux.py,sha256=iNQ-1RlOgXupZ4uPiEvJ__Ro6vKT_fOKja9JrpMrO78,8998
+cache_dit/compile/__init__.py,sha256=FcTVzCeyypl-mxlc59_ehHL3lBNiDAFsXuRoJ-5Cfi0,56
+cache_dit/compile/utils.py,sha256=53KPsMWHyGmHGtw0T4oP0VY4O60cVXOFwFGWTlZrUqI,3857
+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/config.py,sha256=ieOgD9ayz722RjVzk24bSIqS2D6o7TZjGk8KeXV-OLQ,551
+cache_dit/metrics/fid.py,sha256=9Ivtazl6mW0Bon2VXa-Ia5Xj2ewxRD3V1Qkd69zYM3Y,17066
+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-0.2.23.dist-info/licenses/LICENSE,sha256=Dqb07Ik2dV41s9nIdMUbiRWEfDqo7-dQeRiY7kPO8PE,3769
+cache_dit-0.2.23.dist-info/METADATA,sha256=Dq2f8TlyTmv36otIJ2F-fRGkJlZmpW2SY6O14P2AYKo,19772
+cache_dit-0.2.23.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cache_dit-0.2.23.dist-info/entry_points.txt,sha256=FX2gysXaZx6NeK1iCLMcIdP8Q4_qikkIHtEmi3oWn8o,65
+cache_dit-0.2.23.dist-info/top_level.txt,sha256=ZJDydonLEhujzz0FOkVbO-BqfzO9d_VqRHmZU-3MOZo,10
+cache_dit-0.2.23.dist-info/RECORD,,

cache_dit-0.2.21.dist-info/RECORD

@@ -1,32 +0,0 @@
-cache_dit/__init__.py,sha256=lpJ4vUcWuMWE0KXMJpTMxUjkMixifj5jRlp2xPI3n0c,963
-cache_dit/_version.py,sha256=ssMI60XkNnqSio7IM67x0S2AEvggFaGv48yM5LcifrI,706
-cache_dit/logger.py,sha256=0zsu42hN-3-rgGC_C29ms1IvVpV4_b4_SwJCKSenxBE,4304
-cache_dit/primitives.py,sha256=A2iG9YLot3gOsZSPp-_gyjqjLgJvWQRx8aitD4JQ23Y,3877
-cache_dit/utils.py,sha256=UF_vDtOzUb0fbzDlj353amPQSdKYdMNuY_BpMewK-mg,4968
-cache_dit/cache_factory/.gitignore,sha256=5Cb-qT9wsTUoMJ7vACDF7ZcLpAXhi5v-xdcWSRit988,23
-cache_dit/cache_factory/__init__.py,sha256=r2JHx-vPe5eZ8pZFN0Fgl2ZZYO7rSN3MQtTrnuZyasQ,1863
-cache_dit/cache_factory/cache_adapters.py,sha256=qrtRxI__xn2G127c47g-gfD5-s5v-vk291vYRPJGrgM,20775
-cache_dit/cache_factory/cache_blocks.py,sha256=kMEOoNvygzeiM2yvUSAPkKpHeQTOpXQYH2qz34TqXzs,18457
-cache_dit/cache_factory/cache_context.py,sha256=UwrRRGmh1-IuBXD83X7Jyyl7yli4LyHbjprURoE0xE4,39819
-cache_dit/cache_factory/cache_types.py,sha256=vRAIrbtgzeWc9m28oXG9H6Qx8UD3z7aY9vYF2iiW6Jg,2123
-cache_dit/cache_factory/forward_pattern.py,sha256=B2YeqV2t_zo2Ar8m7qimPBjwQgoXHGp2grPZmEAhi8s,1286
-cache_dit/cache_factory/taylorseer.py,sha256=LKSNo2ode69EVo9xrxjxAMEjz0yDGiGADeDYnEqddA8,3987
-cache_dit/cache_factory/utils.py,sha256=Fg55vEMFNXQKGmFBsWfGGm8DW7TjRPKInkb7HlK4naE,1790
-cache_dit/cache_factory/patch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cache_dit/cache_factory/patch/flux.py,sha256=iNQ-1RlOgXupZ4uPiEvJ__Ro6vKT_fOKja9JrpMrO78,8998
-cache_dit/compile/__init__.py,sha256=FcTVzCeyypl-mxlc59_ehHL3lBNiDAFsXuRoJ-5Cfi0,56
-cache_dit/compile/utils.py,sha256=ugHrv3QRieG1xKwcg_pi3yVZF6EpSOEJjRmbnfa7VG0,3779
-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/config.py,sha256=ieOgD9ayz722RjVzk24bSIqS2D6o7TZjGk8KeXV-OLQ,551
-cache_dit/metrics/fid.py,sha256=9Ivtazl6mW0Bon2VXa-Ia5Xj2ewxRD3V1Qkd69zYM3Y,17066
-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-0.2.21.dist-info/licenses/LICENSE,sha256=Dqb07Ik2dV41s9nIdMUbiRWEfDqo7-dQeRiY7kPO8PE,3769
-cache_dit-0.2.21.dist-info/METADATA,sha256=w-_o415q6fDdDw_LR8ZKZhyvdcsGuKAAfYseZ8vpDj0,19908
-cache_dit-0.2.21.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-cache_dit-0.2.21.dist-info/entry_points.txt,sha256=FX2gysXaZx6NeK1iCLMcIdP8Q4_qikkIHtEmi3oWn8o,65
-cache_dit-0.2.21.dist-info/top_level.txt,sha256=ZJDydonLEhujzz0FOkVbO-BqfzO9d_VqRHmZU-3MOZo,10
-cache_dit-0.2.21.dist-info/RECORD,,