ace-step + stable-audio-open: deploy music + SFX generation to irv-ml1

Two new audio-generation stacks alongside the TTS slate:

ace-step :8210 — Apache 2.0 music generation foundation model
(hybrid diffusion + LLM). Lyric-aware multi-minute songs. ~10-12 GB
VRAM during inference, A6000-pinned. Custom Dockerfile patches
upstream's torch/cu126 resolution bug (--extra-index-url cu126 was
falling back to pypi-default cu13 wheels, mismatching torchvision).

stable-audio-open :8211 — Stability AI 1.21B latent-diffusion SFX +
ambience. Up to 47s clips at 44.1 kHz. ~6 GB VRAM in fp16,
A6000-pinned. Custom FastAPI shim around diffusers' StableAudioPipeline
(no upstream HTTP server). Dockerfile pins torchsde explicitly —
diffusers doesn't pull it as a hard dep but
CosineDPMSolverMultistepScheduler needs it.

stacks/stable-audio-open/server.py

@@ -0,0 +1,80 @@
+# FastAPI shim around diffusers' StableAudioPipeline.
+# Single endpoint POST /v1/audio/sfx returns a WAV blob.
+# Model is loaded once on startup and held in process memory.
+import io
+import os
+import time
+from contextlib import asynccontextmanager
+from typing import Optional
+
+import soundfile as sf
+import torch
+from diffusers import StableAudioPipeline
+from fastapi import FastAPI, HTTPException, Response
+from pydantic import BaseModel, Field
+
+MODEL_ID = os.environ.get("SAO_MODEL", "stabilityai/stable-audio-open-1.0")
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+DTYPE = torch.float16 if DEVICE == "cuda" else torch.float32
+
+state: dict = {}
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    print(f"[sao] loading {MODEL_ID} on {DEVICE} ({DTYPE})", flush=True)
+    t0 = time.time()
+    pipe = StableAudioPipeline.from_pretrained(MODEL_ID, torch_dtype=DTYPE)
+    pipe = pipe.to(DEVICE)
+    state["pipe"] = pipe
+    print(f"[sao] loaded in {time.time() - t0:.1f}s", flush=True)
+    yield
+    state.clear()
+
+
+app = FastAPI(lifespan=lifespan)
+
+
+class SfxRequest(BaseModel):
+    prompt: str = Field(..., min_length=1)
+    negative_prompt: Optional[str] = "Low quality."
+    duration: float = Field(10.0, gt=0.5, le=47.0)
+    steps: int = Field(100, ge=10, le=300)
+    seed: Optional[int] = None
+    cfg_scale: float = Field(7.0, gt=0.0, le=20.0)
+
+
+@app.get("/health")
+def health():
+    return {
+        "status": "ok",
+        "model": MODEL_ID,
+        "device": DEVICE,
+        "loaded": "pipe" in state,
+    }
+
+
+@app.post("/v1/audio/sfx")
+def sfx(req: SfxRequest):
+    pipe = state.get("pipe")
+    if pipe is None:
+        raise HTTPException(503, "model not loaded yet")
+
+    generator = None
+    if req.seed is not None:
+        generator = torch.Generator(DEVICE).manual_seed(req.seed)
+
+    audio = pipe(
+        req.prompt,
+        negative_prompt=req.negative_prompt,
+        num_inference_steps=req.steps,
+        audio_end_in_s=req.duration,
+        num_waveforms_per_prompt=1,
+        generator=generator,
+    ).audios
+
+    waveform = audio[0].T.float().cpu().numpy()
+    buf = io.BytesIO()
+    sf.write(buf, waveform, pipe.vae.sampling_rate, format="WAV")
+    buf.seek(0)
+    return Response(content=buf.read(), media_type="audio/wav")