diff --git a/faster_qwen3_tts/predictor_graph.py b/faster_qwen3_tts/predictor_graph.py
index 38a52ca..70851eb 100644
--- a/faster_qwen3_tts/predictor_graph.py
+++ b/faster_qwen3_tts/predictor_graph.py
@@ -13,6 +13,8 @@ Strategy:
 - Unroll the full 15-step loop for deterministic shapes
 - Capture the entire loop as a single CUDA graph
 """
+import os
+
 import torch
 from transformers import StaticCache
 from transformers.masking_utils import create_causal_mask, create_sliding_window_causal_mask
@@ -175,6 +177,11 @@ class PredictorGraph:
         self._init_cache_layers()
         self._build_attention_masks()
 
+        # Opt-in: fuse the 15-step predictor loop with Inductor before graph capture.
+        # ~17% faster streaming on GB10 (0.6B); adds ~1 min to the first warmup.
+        if os.environ.get("TTS_COMPILE_PREDICTOR") == "1":
+            self._full_loop = torch.compile(self._full_loop, dynamic=False)
+
         for _ in range(num_warmup):
             self.static_cache.reset()
             self._full_loop()