[ci]: lower MG3 SSIM test resolution + add L40S device fallback

Two related changes to fastvideo/tests/ssim/test_matrixgame3_similarity.py:

1. Lower MATRIXGAME3_PARAMS height/width from 720x1280 to 352x640
   (matches MatrixGame 2.0 convention from MatrixGame2SamplingParam
   defaults). MATRIXGAME3_FULL_QUALITY_PARAMS remains 720x1280 — it
   derives from SamplingParam.from_pretrained and covers the
   full-quality tier separately. Compute reduction: ~4x vs 720p
   (352*640 / 720*1280 ≈ 0.24).

2. Add fallback_device_prefix='L40S' to resolve_device_reference_folder
   so non-tabled GPUs (B200, etc) fall back to L40S references with a
   clean warning instead of TypeError-crashing at build_generated_output_dir.
   Matches the precedent in fastvideo/tests/ssim/test_sd35_similarity.py.

Together: brings the SSIM test within L40S CI runtime budget AND makes
it runnable locally on B200 dev boxes before the HF reference is seeded.

Followup to PR #1201 review:
#1201 (comment)

Author: SolitaryThinker

fastvideo/tests/ssim/test_matrixgame3_similarity.py

@@ -30,15 +30,16 @@
         ("H200", "H200"),
     ),
     device_name=get_cuda_device_name(),
+    fallback_device_prefix="L40S",
     logger=logger,
 )
 
 
 MATRIXGAME3_PARAMS = {
     "num_gpus": 1,
     "model_path": "FastVideo/Matrix-Game-3.0-Base-Distilled-Diffusers",
-    "height": 720,
-    "width": 1280,
+    "height": 352,
+    "width": 640,
     "num_frames": 57,
     "num_inference_steps": 3,
     "guidance_scale": 5.0,