feat(trt): 30s decoder profile for the loop-focused workflow

acestep/paths.py

@@ -312,6 +312,19 @@ def trt_engine_path(engine_name: str) -> Path:
 # scripts/benchmarks/vram_60s_vs_240s_results.md. Pick the smallest profile
 # that fits the audio (see `select_trt_engines` and `available_trt_engines`).
 _TRT_ENGINE_PROFILES: dict[float, dict[str, str]] = {
+    # 30s decoder for the loop-focused / short-source workflow: a smaller
+    # seq_max (750 frames vs 1500) reserves less DiT activation workspace
+    # (VRAM headroom) and is opt-tuned at 750 for lower param-update
+    # latency. The VAE engines are intentionally the 60s builds — the
+    # walk-window path keeps vae_encode sized to the full song, and the
+    # 60s vae_decode already accepts ≤1500 frames, so 750-frame decodes
+    # need no dedicated engine. Build with
+    # ``python -m acestep.engine.trt.build --all --duration 30 --decoder-only``.
+    30.0: {
+        "decoder": "spectral_decoder_mixed_refit_b8_30s",
+        "vae_encode": "vae_encode_fp16_60s",
+        "vae_decode": "vae_decode_fp16_60s",
+    },
     60.0: {
         "decoder": "spectral_decoder_mixed_refit_b8_60s",
         "vae_encode": "vae_encode_fp16_60s",

docs/TRT.md

@@ -176,6 +176,25 @@ Build only decoder engines:
 uv run python -m acestep.engine.trt.build --all --decoder-only --duration 60
 ```
 
+Build the 30s loop-window decoder (decoder-only):
+
+```powershell
+uv run python -m acestep.engine.trt.build --all --decoder-only --duration 30
+```
+
+The `30.0` profile in `acestep/paths.py` serves the loop-focused /
+short-source workflow (`walk_window_s = 30`, or any source ≤ 30s). Its
+`seq_max` is 750 frames (vs 1500 for 60s), so the DiT context reserves
+less activation workspace and is opt-tuned at 750 for lower
+param-update latency. It is **decoder-only**: the profile reuses the
+existing 60s VAE engines, because the walk-window path keeps
+`vae_encode` sized to the full song and the 60s `vae_decode` already
+accepts ≤ 1500-frame inputs. (A dedicated sub-60s VAE engine is not
+needed and currently fails the TRT optimization-profile check on
+Blackwell — see `RTX 5090 / Blackwell VAE Builds` above.) Measured on a
+5090 vs running the same 750-frame window on the 60s engine: ~12% faster
+warm generate (0.121s vs 0.137s) and ~0.25 GB less process VRAM.
+
 Build only VAE engines:
 
 ```powershell