diff --git a/docs/user_guide/diffusion_features.md b/docs/user_guide/diffusion_features.md index c34c1338c..e5da3c294 100644 --- a/docs/user_guide/diffusion_features.md +++ b/docs/user_guide/diffusion_features.md @@ -116,7 +116,7 @@ The following tables show which models support each feature: | **FLUX.1-dev** | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | | **FLUX.1-schnell** | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | | **FLUX.2-klein** | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | -| **FLUX.1-Kontext-dev** | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | +| **FLUX.1-Kontext-dev** | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | | **FLUX.2-dev** | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | | **GLM-Image** | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | | **Hidream-I1-Full** | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | diff --git a/tests/e2e/online_serving/test_flux_kontext_expansion.py b/tests/e2e/online_serving/test_flux_kontext_expansion.py index 17d4b0263..4a8a9ab98 100644 --- a/tests/e2e/online_serving/test_flux_kontext_expansion.py +++ b/tests/e2e/online_serving/test_flux_kontext_expansion.py @@ -45,6 +45,19 @@ def _get_diffusion_feature_cases(model: str): id="parallel_cfg_2", marks=PARALLEL_FEATURE_MARKS, ), + pytest.param( + OmniServerParams( + model=model, + server_args=[ + "--tensor-parallel-size", + "2", + "--enable-cpu-offload", + "--cache-backend", + "cache_dit", + ], + ), + id="parallel_002", + ), ] diff --git a/vllm_omni/diffusion/models/flux/pipeline_flux_kontext.py b/vllm_omni/diffusion/models/flux/pipeline_flux_kontext.py index 15f0e4e0c..5aff911c6 100644 --- a/vllm_omni/diffusion/models/flux/pipeline_flux_kontext.py +++ b/vllm_omni/diffusion/models/flux/pipeline_flux_kontext.py @@ -641,6 +641,11 @@ class FluxKontextPipeline( num_inference_steps = req.sampling_params.num_inference_steps or num_inference_steps sigmas = req.sampling_params.sigmas or sigmas guidance_scale = req.sampling_params.guidance_scale or guidance_scale + num_images_per_prompt = ( + req.sampling_params.num_outputs_per_prompt + if req.sampling_params.num_outputs_per_prompt > 0 + else num_images_per_prompt + ) true_cfg_scale = ( req.sampling_params.true_cfg_scale if req.sampling_params.true_cfg_scale is not None else true_cfg_scale )