[Feat] Enable DiT tensor parallel for Diffusion Pipeline(Z-Image) (#735)

Signed-off-by: dongbo910220 <1275604947@qq.com>
Signed-off-by: dongbo910220 <32610838+dongbo910220@users.noreply.github.com>
Signed-off-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>

examples/offline_inference/text_to_image/text_to_image.py

@@ -88,6 +88,17 @@ def parse_args() -> argparse.Namespace:
         choices=[1, 2],
         help="Number of GPUs used for classifier free guidance parallel size.",
     )
+    parser.add_argument(
+        "--enforce_eager",
+        action="store_true",
+        help="Disable torch.compile and force eager execution.",
+    )
+    parser.add_argument(
+        "--tensor_parallel_size",
+        type=int,
+        default=1,
+        help="Number of GPUs used for tensor parallelism (TP) inside the DiT.",
+    )
     return parser.parse_args()
 
 
@@ -131,7 +142,10 @@ def main():
 
     # assert args.ring_degree == 1, "Ring attention is not supported yet"
     parallel_config = DiffusionParallelConfig(
-        ulysses_degree=args.ulysses_degree, ring_degree=args.ring_degree, cfg_parallel_size=args.cfg_parallel_size
+        ulysses_degree=args.ulysses_degree,
+        ring_degree=args.ring_degree,
+        cfg_parallel_size=args.cfg_parallel_size,
+        tensor_parallel_size=args.tensor_parallel_size,
     )
 
     omni = Omni(
@@ -141,6 +155,7 @@ def main():
         cache_backend=args.cache_backend,
         cache_config=cache_config,
         parallel_config=parallel_config,
+        enforce_eager=args.enforce_eager,
     )
 
     # Time profiling for generation
@@ -150,7 +165,8 @@ def main():
     print(f"  Inference steps: {args.num_inference_steps}")
     print(f"  Cache backend: {args.cache_backend if args.cache_backend else 'None (no acceleration)'}")
     print(
-        f"  Parallel configuration: ulysses_degree={args.ulysses_degree}, ring_degree={args.ring_degree}, cfg_parallel_size={args.cfg_parallel_size}"
+        f"  Parallel configuration: tensor_parallel_size={args.tensor_parallel_size}, "
+        f"ulysses_degree={args.ulysses_degree}, ring_degree={args.ring_degree}, cfg_parallel_size={args.cfg_parallel_size}"
     )
     print(f"  Image size: {args.width}x{args.height}")
     print(f"{'=' * 60}\n")