vllm-omni

0 Fork 0

Files

T

Isotr0py 3affc7766d Enable VAE tiling for Qwen-Image-2.1 (#5 )

* init

Signed-off-by: Isotr0py <mozf@inferact.ai>

* fix

Signed-off-by: Isotr0py <mozf@inferact.ai>

* test(diffusion): add Qwen-Image-2.1 unit tests

Signed-off-by: Isotr0py <mozf@inferact.ai>

* fix(diffusion): Qwen-Image-2.1 VAE spatial ratio, tiling e2e verification

- AutoencoderKLQwenImage21: derive spatial_compression_ratio from the
  architecture (2 ** len(temperal_downsample) = 16x) instead of trusting
  the checkpoint's scale_factor_spatial=8, which corrupted tiled
  decode/encode geometry (output cropped to half size) and tiling gating.
- pipeline: _read_vae_scale_factor prefers the architecture-derived value
  for the same reason.
- models/qwen_image_21/__init__: lazy exports to break the circular import
  distributed VAE -> package __init__ -> pipeline -> distributed VAE.
- Add VAE unit tests: ratio derivation, tiled vs untiled decode/encode
  consistency, distributed tile_split/exec/merge == tiled_decode.
- e2e matrix (GB200, seed 42, 20 steps) all green; see e2e_out/qwen21_vae/.
- examples: qwen_image_21_edit.py gains --vae-use-tiling.
- docs: mark VAE patch-parallel verified for Qwen-Image-2.1; recipe notes
  the default-tile banding limitation at 2048px+.

* clean tests

Signed-off-by: Isotr0py <mozf@inferact.ai>

* fix cudnn determination

Signed-off-by: Isotr0py <mozf@inferact.ai>

---------

Signed-off-by: Isotr0py <mozf@inferact.ai>

2026-09-18 10:02:50 +08:00

diffusion

[Bugfix] Resolve #6931 hub FA3 on torch 2.13 via kernels 0.16.1 (#7185 )

2026-09-09 10:20:34 +00:00

examples

[Doc] Document num_outputs_per_prompt for /v1/videos (#7341 )

2026-09-10 08:00:13 +08:00

quantization

[Model] FP8 Support For Boogu-Image (#6925 )

2026-09-06 04:48:38 +00:00

diffusion_features.md

Enable VAE tiling for Qwen-Image-2.1 (#5 )