Kandinsky6 (#8537)

Signed-off-by: leffff <levnovitskiy@gmail.com>
Signed-off-by: Artem Borisov <divotionchannel@gmail.com>
Co-authored-by: leffff <levnovitskiy@gmail.com>
Co-authored-by: Artem Borisov <divotionchannel@gmail.com>
This commit is contained in:
authored and GitHub committed 2026-10-06 15:55:15 +08:00
1 parent 1f63e97a40
commit 5f95115e70
38 files changed
+8574 -8

No files matched your search

+30
View File
@@ -908,6 +908,35 @@ def enable_cache_for_mammothmoda2(pipeline: Any, cache_config: Any) -> CacheDiTE
return CacheDiTEnableResult(refresh=refresh, targets=(block_adapter,))
def enable_cache_for_kandinsky6(pipeline: Any, cache_config: Any) -> RefreshCacheContextFunc:
"""Cache-DiT over K6 visual blocks only.
Text and audio block lists are not one residual chain with the visual
stack. If the block adapter rejects the fused ``(video, audio)`` return,
fall back to the same step-level velocity cache MagCache uses.
"""
transformer = pipeline.transformer
block_adapter = BlockAdapter(
transformer=transformer,
blocks=[transformer.visual_transformer_blocks],
forward_pattern=[ForwardPattern.Pattern_0],
has_separate_cfg=True,
check_forward_pattern=False,
)
try:
return enable_cache_for_dit(pipeline, cache_config, block_adapter)
except Exception as exc:
logger.warning("Cache-DiT block adapter failed for Kandinsky 6 (%s); using step cache", exc)
from vllm_omni.diffusion.models.kandinsky6.cache_accel import attach_mag_cache
attach_mag_cache(transformer, threshold=0.24, max_skip_steps=3, retention_ratio=0.1)
def _refresh(*_args, **_kwargs):
return None
return _refresh
def register_custom_dit_enablers() -> None:
"""Register model-specific Cache-DiT enablers.
@@ -925,6 +954,7 @@ def register_custom_dit_enablers() -> None:
"Cosmos3OmniDiffusersPipeline": enable_cache_for_cosmos3,
"Cosmos3OmniPipeline": enable_cache_for_cosmos3,
"Krea2Pipeline": enable_cache_for_krea2,
"Kandinsky6TI2VAPipeline": enable_cache_for_kandinsky6,
"Magi2Pipeline": enable_cache_for_magi2,
"MammothModa2DiTPipeline": enable_cache_for_mammothmoda2,
}
+14 -1
View File
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
"""
MagCache backend implementation.
@@ -73,6 +73,19 @@ class MagCacheBackend(CacheBackend):
transformer = pipeline.transformer
transformer_type = transformer.__class__.__name__
if transformer_type == "Kandinsky6Transformer3DModel":
from vllm_omni.diffusion.models.kandinsky6.cache_accel import attach_mag_cache
attach_mag_cache(
transformer,
threshold=self.config.mag_threshold,
max_skip_steps=self.config.mag_max_skip_steps,
retention_ratio=self.config.mag_retention_ratio,
)
self._registered = True
logger.info("MagCache: Kandinsky 6 step-cache attached (visual/audio velocity reuse)")
return
num_inference_steps = self.config.num_inference_steps or 28
mag_ratios = self.config.mag_ratios
+4 -1
View File
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
"""
Hook-based MagCache implementation for vLLM-Omni.
@@ -543,9 +543,12 @@ def apply_mag_cache_hook(
state_manager = StateManager(MagCacheState, (), {})
remaining_blocks = []
allowed = getattr(module, "_magcache_block_attrs", None)
for name, submodule in module.named_children():
if not isinstance(submodule, torch.nn.ModuleList):
continue
if allowed is not None and name not in allowed:
continue
for index, block in enumerate(submodule):
remaining_blocks.append((f"{name}.{index}", block))
+20 -1
View File
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
"""
TeaCache backend implementation.
@@ -143,11 +143,30 @@ def enable_flux2_klein_teacache(pipeline: Any, config: DiffusionCacheConfig) ->
)
def enable_kandinsky6_teacache(pipeline: Any, config: DiffusionCacheConfig) -> None:
"""TeaCache for Kandinsky 6 via the denoise-loop step cache.
Coefficients are uncalibrated (see ``K6_TEACACHE_COEFFICIENTS``).
"""
from vllm_omni.diffusion.models.kandinsky6.cache_accel import attach_tea_cache
attach_tea_cache(
pipeline.transformer,
rel_l1_thresh=config.rel_l1_thresh if config.rel_l1_thresh is not None else 0.2,
coefficients=tuple(config.coefficients) if config.coefficients is not None else None,
)
logger.info(
"TeaCache: Kandinsky 6 step-cache attached (uncalibrated coefficients, thresh=%s)",
config.rel_l1_thresh,
)
CUSTOM_TEACACHE_ENABLERS = {
"BagelPipeline": enable_bagel_teacache,
"Flux2KleinPipeline": enable_flux2_klein_teacache,
"HunyuanImage3Pipeline": enable_hunyuan_image3_teacache,
"MammothModa2DiTPipeline": enable_mammoth_moda2_teacache,
"Kandinsky6TI2VAPipeline": enable_kandinsky6_teacache,
"MiniMaxH3Pipeline": enable_minimax_h3_teacache,
"SenseNovaU1Pipeline": enable_sensenova_u1_teacache,
}
+10 -1
View File
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
from dataclasses import dataclass
@@ -8,6 +8,15 @@ from dataclasses import dataclass
# Source: TeaCache paper and ComfyUI-TeaCache empirical tuning
_MODEL_COEFFICIENTS = {
# FLUX transformer coefficients from TeaCache paper
# Uncalibrated stand-in so Kandinsky 6 TeaCache can be enabled.
# Copied from Qwen-Image; refit before treating skips as quality-neutral.
"Kandinsky6Transformer3DModel": [
-4.50000000e02,
2.80000000e02,
-4.50000000e01,
3.20000000e00,
-2.00000000e-02,
],
"FluxTransformer2DModel": [
4.98651651e02,
-2.83781631e02,