diff --git a/compose.spark.yml b/compose.spark.yml
index f4d6017..c177102 100644
--- a/compose.spark.yml
+++ b/compose.spark.yml
@@ -28,4 +28,7 @@ services:
       - "8001:8000"
     environment:
       H3_DISABLE_MMAP: "1"
-    command: ["python", "/opt/h3-blackwell-runtime/tools/serve_hot_runtime.py", "--host", "0.0.0.0", "--port", "8000", "--attention", "sage2", "--warmup"]
+      H3_NVFP4_SCALE_BACKEND: "vortex"
+      H3_NVFP4_SCALE_VERSION: "1"
+      H3_SOL_QKV_LAYOUT: "native"
+    command: ["python", "/opt/h3-blackwell-runtime/tools/serve_hot_runtime.py", "--host", "0.0.0.0", "--port", "8000", "--attention", "sol_attn", "--warmup"]
diff --git a/tools/direct_t2v_preview.py b/tools/direct_t2v_preview.py
index 378c5be..49e313e 100644
--- a/tools/direct_t2v_preview.py
+++ b/tools/direct_t2v_preview.py
@@ -14,7 +14,7 @@ import torch
 
 from h3_blackwell_runtime.checkpoint import H3Checkpoint
 from h3_blackwell_runtime.audio_vae_decoder import MiniMaxH3AudioVAE
-from h3_blackwell_runtime.attention import AVAILABLE_BACKENDS
+from h3_blackwell_runtime.attention import AVAILABLE_BACKENDS, DEFAULT_ATTENTION_BACKEND
 from h3_blackwell_runtime.block import configure_mlp_chunking
 from h3_blackwell_runtime.denoiser import H3PackedDenoiser
 from h3_blackwell_runtime.packing import H3PromptPacker
@@ -33,7 +33,7 @@ parser.add_argument("--height", type=int, default=192)
 parser.add_argument("--frames", type=int, default=22)
 parser.add_argument("--steps", type=int, default=12)
 parser.add_argument("--seed", type=int, default=440204)
-parser.add_argument("--attention", choices=AVAILABLE_BACKENDS, default="sage2")
+parser.add_argument("--attention", choices=AVAILABLE_BACKENDS, default=DEFAULT_ATTENTION_BACKEND)
 parser.add_argument("--model-timesteps-capture", type=Path, help="Directory containing captured input_XX.pt H3 timesteps for strict parity checks.")
 parser.add_argument("--progress", action="store_true", help="Print per-step sampler progress.")
 parser.add_argument("--profile-memory", action="store_true")