cache-dit 0.2.18__py3-none-any.whl → 0.2.19__py3-none-any.whl

cache_dit/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.2.18'
-__version_tuple__ = version_tuple = (0, 2, 18)
+__version__ = version = '0.2.19'
+__version_tuple__ = version_tuple = (0, 2, 19)
 
 __commit_id__ = commit_id = None

cache_dit/cache_factory/cache_adapters.py

@@ -631,7 +631,8 @@ class UnifiedCacheAdapter:
                 pattern_id = list(unique_pattern_ids)[0]
                 pattern = selected_patterns[pattern_id]
                 logger.info(
-                    f"Match cache pattern: IN({pattern['IN']}, OUT({pattern['OUT']}))"
+                    f"Match Block Forward Pattern: {transformer_blocks[0].__class__.__name__}"
+                    f"\n IN({pattern['IN']}, \nOUT({pattern['OUT']}))"
                 )
 
         return pattern_matched

cache_dit/cache_factory/patch/flux.py

@@ -230,7 +230,7 @@ def maybe_patch_flux_transformer(
     for block in blocks:
         if isinstance(block, FluxSingleTransformerBlock):
             forward_parameters = inspect.signature(
-                blocks.forward
+                block.forward
             ).parameters.keys()
             if "encoder_hidden_states" not in forward_parameters:
                 block.forward = __patch_single_forward__.__get__(block)

{cache_dit-0.2.18.dist-info → cache_dit-0.2.19.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cache_dit
-Version: 0.2.18
+Version: 0.2.19
 Summary: 🤗 CacheDiT: An Unified and Training-free Cache Acceleration Toolbox for Diffusion Transformers
 Author: DefTruth, vipshop.com, etc.
 Maintainer: DefTruth, vipshop.com, etc
@@ -61,16 +61,15 @@ Dynamic: requires-python
   </p>
 </div> 
 
-
 ## 🔥News  
 
-- [2025-08-19] 🔥[**Qwen-Image-Edit**](https://github.com/QwenLM/Qwen-Image) **~2x⚡️** speedup! Check example [run_qwen_image_edit.py](./examples/run_qwen_image_edit.py).
+- [2025-08-19] 🔥[**Qwen-Image-Edit**](https://github.com/QwenLM/Qwen-Image) **2x⚡️** speedup! Check example [run_qwen_image_edit.py](./examples/run_qwen_image_edit.py).
 - [2025-08-18] 🎉Early **[Unified Cache APIs](#unified)** released! Check [Qwen-Image w/ UAPI](./examples/run_qwen_image_uapi.py) as an example.
 - [2025-08-12] 🎉First caching mechanism in [QwenLM/Qwen-Image](https://github.com/QwenLM/Qwen-Image) with **[cache-dit](https://github.com/vipshop/cache-dit)**, check the [PR](https://github.com/QwenLM/Qwen-Image/pull/61). 
-- [2025-08-11] 🔥[**Qwen-Image**](https://github.com/QwenLM/Qwen-Image) **~1.8x⚡️** speedup! Please refer [run_qwen_image.py](./examples/run_qwen_image.py) as an example.
-- [2025-08-10] 🔥[FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) is supported! Please refer [run_flux_kontext.py](./examples/run_flux_kontext.py) as an example.
+- [2025-08-11] 🔥[**Qwen-Image**](https://github.com/QwenLM/Qwen-Image) **1.8x⚡️** speedup! Please refer [run_qwen_image.py](./examples/run_qwen_image.py) as an example.
+- [2025-08-10] 🔥[**FLUX.1-Kontext-dev**](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) is supported! Please refer [run_flux_kontext.py](./examples/run_flux_kontext.py) as an example.
 - [2025-07-18] 🎉First caching mechanism in [🤗huggingface/flux-fast](https://github.com/huggingface/flux-fast) with **[cache-dit](https://github.com/vipshop/cache-dit)**, check the [PR](https://github.com/huggingface/flux-fast/pull/13). 
-- [2025-07-13] **[🤗flux-faster](https://github.com/xlite-dev/flux-faster)** is released! **3.3x** speedup for FLUX.1 on NVIDIA L20 with `cache-dit`.
+- [2025-07-13] **[🤗flux-faster](https://github.com/xlite-dev/flux-faster)** is released! **3.3x** speedup for FLUX.1 on NVIDIA L20 with **[cache-dit](https://github.com/vipshop/cache-dit)**.
 
 ## 📖Contents 
 
@@ -130,28 +129,28 @@ Currently, **cache-dit** library supports almost **Any** Diffusion Transformers
 
 <div id="unified"></div>  
 
+Currently, for any **Diffusion** models with **Transformer Blocks** that match the specific **Input/Output patterns**, we can use the **Unified Cache APIs** from **cache-dit**, namely, the `cache_dit.enable_cache(...)` API. The supported patterns are listed as follows:
 
-Currently, for any **Diffusion** models with **Transformer Blocks** that match the specific **Input/Output pattern**, we can use the **Unified Cache APIs** from **cache-dit**. The supported patterns are listed as follows:
-
-```bash
+```python
 (IN: hidden_states, encoder_hidden_states, ...) -> (OUT: hidden_states, encoder_hidden_states)  
 (IN: hidden_states, encoder_hidden_states, ...) -> (OUT: encoder_hidden_states, hidden_states)  
 (IN: hidden_states, encoder_hidden_states, ...) -> (OUT: hidden_states)
 (IN: hidden_states, ...) -> (OUT: hidden_states) # TODO, DiT, Lumina2, etc. 
 ```
 
-Please refer to [Qwen-Image w/ UAPI](./examples/run_qwen_image_uapi.py) as an example. The `pipe` parameter can be **Any** Diffusion Pipelines. The **Unified Cache APIs** are currently in the experimental phase, please stay tuned for updates. 
+After the `cache_dit.enable_cache(...)` API is called, you just need to call the pipe as normal. The `pipe` param can be **any** Diffusion Pipeline. Please refer to [Qwen-Image](./examples/run_qwen_image_uapi.py) as an example. The **Unified Cache APIs** are currently in the experimental phase; please stay tuned for updates.
 
 ```python
 import cache_dit
-from diffusers import DiffusionPipeline # Can be [Any] Diffusion Pipeline
+from diffusers import DiffusionPipeline 
 
+# can be any diffusion pipeline
 pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image")
 
-# One line code with default cache options.
+# one line code with default cache options.
 cache_dit.enable_cache(pipe) 
 
-# Or, enable cache with custom setting.
+# or, enable cache with custom settings.
 cache_dit.enable_cache(
     pipe, transformer=pipe.transformer,
     blocks=pipe.transformer.transformer_blocks,
@@ -159,28 +158,22 @@ cache_dit.enable_cache(
     **cache_dit.default_options(),
 )
 
-# summary cache stats.
-cache_dit.summary(pipe)
-```
-
-After finishing each inference of `pipe(...)`, you can call the `cache_dict.summary` API on pipe to get the details of the cache stats for the current inference (markdown table format). You can set `details` param as `True` to show more details of cache stats.
+# just call the pipe as normal.
+output = pipe(...)
 
-```bash
-🤗Cache Options: QwenImagePipeline
+# then, summary the cache stats.
+stats = cache_dit.summary(pipe)
+```
 
-{'Fn_compute_blocks': 8, 'Bn_compute_blocks': 0, 'non_compute_blocks_diff_threshold': 0.08, 'max_Fn_compute_blocks': -1, 'max_Bn_compute_blocks': -1, 'residual_diff_threshold': 0.12, 'l1_hidden_states_diff_threshold': None, 'important_condition_threshold': 0.0, 'enable_alter_cache': False, 'is_alter_cache': True, 'alter_residual_diff_threshold': 1.0, 'downsample_factor': 1, 'num_inference_steps': -1, 'warmup_steps': 8, 'max_cached_steps': -1, 'executed_steps': 0, 'transformer_executed_steps': 0, 'enable_taylorseer': True, 'enable_encoder_taylorseer': True, 'taylorseer_cache_type': 'residual', 'taylorseer': None, 'encoder_tarlorseer': None, 'do_separate_classifier_free_guidance': True, 'cfg_compute_first': False, 'cfg_diff_compute_separate': True, 'cfg_taylorseer': None, 'cfg_encoder_taylorseer': None, 'Fn_compute_blocks_ids': [], 'Bn_compute_blocks_ids': [], 'taylorseer_kwargs': {'n_derivatives': 4, 'warmup_steps': 8}}
+After finishing each inference of `pipe(...)`, you can call the `cache_dit.summary(...)` API on pipe to get the details of the cache stats for the current inference (markdown table format). You can set `details` param as `True` to show more details of cache stats.
 
+```python
 ⚡️Cache Steps and Residual Diffs Statistics: QwenImagePipeline
 
 | Cache Steps | Diffs P00 | Diffs P25 | Diffs P50 | Diffs P75 | Diffs P95 |
 |-------------|-----------|-----------|-----------|-----------|-----------|
 | 23          | 0.04      | 0.082     | 0.115     | 0.152     | 0.245     |
-
-⚡️CFG Cache Steps and Residual Diffs Statistics: QwenImagePipeline
-
-| CFG Cache Steps | Diffs P00 | Diffs P25 | Diffs P50 | Diffs P75 | Diffs P95 |
-|-----------------|-----------|-----------|-----------|-----------|-----------|
-| 22              | 0.045     | 0.077     | 0.112     | 0.148     | 0.245     |
+...
 ```
 
 ## ⚡️DBCache: Dual Block Cache  

{cache_dit-0.2.18.dist-info → cache_dit-0.2.19.dist-info}/RECORD

@@ -1,17 +1,17 @@
 cache_dit/__init__.py,sha256=TvZI861ipGnYaOEHJA0Og-ksRUGNCld-PGy_NgjcKZE,641
-cache_dit/_version.py,sha256=dCdYCOiddErhHj0N8E7eGD9CFxW2AjdU7N-JosKZW0o,706
+cache_dit/_version.py,sha256=32XF9c5EeiOUdyiWeKcwkXTWZQBgtvbmKx8wZoDEW0o,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=yybhUTGPfeCoIVZzpoefZ2ypvH8de-10UhPls81ceG4,4800
 cache_dit/cache_factory/.gitignore,sha256=5Cb-qT9wsTUoMJ7vACDF7ZcLpAXhi5v-xdcWSRit988,23
 cache_dit/cache_factory/__init__.py,sha256=f4IUOgEALTEBb9UOHtXoGwqKrDb2ZhI_dHkiIrni1Xc,1586
-cache_dit/cache_factory/cache_adapters.py,sha256=twzxe6VYB-9iRwU1Fct15mm5pdPNOyqBoLRBscnYZHA,23508
+cache_dit/cache_factory/cache_adapters.py,sha256=-bFMOfIPdfWKTAfF533PuLYaDl1wq8RNUAXJn--Rm7I,23587
 cache_dit/cache_factory/cache_blocks.py,sha256=9jgK2IT0Y_AlbhJLnhgA47lOxQNwNizDgHve45818gg,18390
 cache_dit/cache_factory/cache_context.py,sha256=f-ihx14NXIZNakN2b_dduegRpJr5SwcPtc2PqnpDdUY,39818
 cache_dit/cache_factory/taylorseer.py,sha256=LKSNo2ode69EVo9xrxjxAMEjz0yDGiGADeDYnEqddA8,3987
 cache_dit/cache_factory/utils.py,sha256=iQg3dqBfQTGkvMdKeO5-YmzkQO5LBSoZ8sYKwQA_7_I,1805
 cache_dit/cache_factory/patch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cache_dit/cache_factory/patch/flux.py,sha256=eTdq-3limKHgwtVCILkZTwt9FwYUhH7_VlhKnfu55BU,8999
+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
@@ -22,9 +22,9 @@ cache_dit/metrics/fid.py,sha256=9Ivtazl6mW0Bon2VXa-Ia5Xj2ewxRD3V1Qkd69zYM3Y,1706
 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-0.2.18.dist-info/licenses/LICENSE,sha256=Dqb07Ik2dV41s9nIdMUbiRWEfDqo7-dQeRiY7kPO8PE,3769
-cache_dit-0.2.18.dist-info/METADATA,sha256=8U_a77k97X2b_nV1X7VDjusKLAAnAbHA-6eYhJ4wiqA,21940
-cache_dit-0.2.18.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-cache_dit-0.2.18.dist-info/entry_points.txt,sha256=FX2gysXaZx6NeK1iCLMcIdP8Q4_qikkIHtEmi3oWn8o,65
-cache_dit-0.2.18.dist-info/top_level.txt,sha256=ZJDydonLEhujzz0FOkVbO-BqfzO9d_VqRHmZU-3MOZo,10
-cache_dit-0.2.18.dist-info/RECORD,,
+cache_dit-0.2.19.dist-info/licenses/LICENSE,sha256=Dqb07Ik2dV41s9nIdMUbiRWEfDqo7-dQeRiY7kPO8PE,3769
+cache_dit-0.2.19.dist-info/METADATA,sha256=cCnv_b_F06xdttqdHhnbmPDpF_xRgz-O03tYfvzGGrI,20910
+cache_dit-0.2.19.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cache_dit-0.2.19.dist-info/entry_points.txt,sha256=FX2gysXaZx6NeK1iCLMcIdP8Q4_qikkIHtEmi3oWn8o,65
+cache_dit-0.2.19.dist-info/top_level.txt,sha256=ZJDydonLEhujzz0FOkVbO-BqfzO9d_VqRHmZU-3MOZo,10
+cache_dit-0.2.19.dist-info/RECORD,,