Prepare isolated YuE2 music evaluation

2026-09-10 21:25:59 +02:00
parent 6bd6c48a95
commit 1904f2104f
9 changed files with 102 additions and 263 deletions
@@ -1,22 +0,0 @@
-FROM pytorch/pytorch:2.9.1-cuda12.8-cudnn9-runtime
-
-ARG HEARTLIB_COMMIT=3783bdb8441f2c298b1e64c8651173aac200361c
-
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends git ffmpeg curl \
-    && rm -rf /var/lib/apt/lists/*
-
-RUN git clone https://github.com/HeartMuLa/heartlib.git /opt/heartlib \
-    && git -C /opt/heartlib checkout "${HEARTLIB_COMMIT}" \
-    && pip install --no-cache-dir -e /opt/heartlib \
-    && pip install --no-cache-dir gradio==5.49.1 uvicorn==0.35.0
-
-COPY app.py /opt/app/app.py
-
-WORKDIR /opt/app
-ENV PYTHONUNBUFFERED=1 \
-    HEARTMULA_MODEL_PATH=/models/ckpt \
-    HEARTMULA_OUTPUT_DIR=/output
-
-EXPOSE 7860
-CMD ["python", "/opt/app/app.py"]
@@ -1,52 +0,0 @@
-# HeartMuLa 3B quality test
-
-Reversible A/B test of the public
-`HeartMuLa/HeartMuLa-oss-3B-happy-new-year` model with
-`HeartMuLa/HeartCodec-oss-20260123`.
-
-The model and codec are deliberately split across Athena's GPUs:
-
- HeartMuLa BF16: RTX 5080 (`cuda:0` inside the container)
- HeartCodec FP32: RTX 3060 (`cuda:1` inside the container)
-
-The public model does not yet support reference-audio conditioning. Pure
-instrumental generation is exposed as an explicitly experimental option.
-Generated files are lossless 48-kHz WAV files under `/data/music/heartmula`.
-
-The container intentionally has no `com.mike-ai.music-worker` label while it
-is being evaluated. This prevents it from conflicting with the production
-profile controller's single ACE-Step worker.
-
-## Checkpoints
-
-The expected persistent layout on Athena is:
-
-```text
-/data/models/heartmula/ckpt/
-├── HeartMuLa-oss-3B/
-├── HeartCodec-oss/
-├── gen_config.json
-└── tokenizer.json
-```
-
-## Test operation
-
-Only after the current music worker has been stopped:
-
-```sh
-cd /opt/mike-ai/heartmula-3b
-docker compose up -d heartmula-test
-docker compose logs -f heartmula-test
-```
-
-The temporary test UI listens locally on port `7863`. During the listening
-test it is proxied through Athena's existing WireGuard gateway; permanent
-dashboard/gateway integration is deliberately deferred until the audio has
-been accepted. Stop it with:
-
-```sh
-docker compose down
-```
-
-Do not remove ACE-Step or change the dashboard/profile controller until the
-A/B test has been accepted.
@@ -1,148 +0,0 @@
-from __future__ import annotations
-
-import os
-import threading
-import time
-import uuid
-from pathlib import Path
-
-import gradio as gr
-import soundfile as sf
-import torch
-import uvicorn
-from fastapi import FastAPI
-from heartlib import HeartMuLaGenPipeline
-
-
-MODEL_PATH = os.environ.get("HEARTMULA_MODEL_PATH", "/models/ckpt")
-OUTPUT_DIR = Path(os.environ.get("HEARTMULA_OUTPUT_DIR", "/output"))
-MULA_DEVICE = os.environ.get("HEARTMULA_MULA_DEVICE", "cuda:0")
-CODEC_DEVICE = os.environ.get("HEARTMULA_CODEC_DEVICE", "cuda:1")
-
-OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
-
-pipeline: HeartMuLaGenPipeline | None = None
-load_error = ""
-generation_lock = threading.Lock()
-
-
-class AthenaHeartMuLaPipeline(HeartMuLaGenPipeline):
-    """Write 24-bit WAV directly; torch 2.9 otherwise requires TorchCodec."""
-
-    def postprocess(self, model_outputs, save_path: str):
-        frames = model_outputs["frames"].to(self.codec_device)
-        wav = self.codec.detokenize(frames)
-        self._unload()
-        audio = wav.to(torch.float32).cpu().numpy().T
-        sf.write(save_path, audio, 48_000, format="WAV", subtype="PCM_24")
-
-
-def load_pipeline() -> None:
-    global pipeline, load_error
-    try:
-        pipeline = AthenaHeartMuLaPipeline.from_pretrained(
-            MODEL_PATH,
-            device={
-                "mula": torch.device(MULA_DEVICE),
-                "codec": torch.device(CODEC_DEVICE),
-            },
-            dtype={"mula": torch.bfloat16, "codec": torch.float32},
-            version="3B",
-            lazy_load=False,
-        )
-    except Exception as exc:
-        load_error = f"{type(exc).__name__}: {exc}"
-        raise
-
-
-def generate(
-    tags: str,
-    lyrics: str,
-    instrumental: bool,
-    duration_seconds: int,
-    topk: int,
-    temperature: float,
-    cfg_scale: float,
-):
-    if pipeline is None:
-        raise gr.Error(f"Modell ist nicht bereit. {load_error}".strip())
-    tags = ",".join(part.strip() for part in tags.split(",") if part.strip())
-    if not tags:
-        raise gr.Error("Bitte mindestens ein Musik-Tag angeben.")
-    if instrumental:
-        effective_lyrics = "[Instrumental]"
-    else:
-        effective_lyrics = lyrics.strip()
-        if not effective_lyrics:
-            raise gr.Error("Für ein Lied mit Gesang fehlt der Liedtext.")
-
-    target = OUTPUT_DIR / f"heartmula-{int(time.time())}-{uuid.uuid4().hex[:8]}.wav"
-    with generation_lock, torch.inference_mode():
-        pipeline(
-            {"lyrics": effective_lyrics, "tags": tags},
-            max_audio_length_ms=int(duration_seconds) * 1000,
-            save_path=str(target),
-            topk=int(topk),
-            temperature=float(temperature),
-            cfg_scale=float(cfg_scale),
-        )
-    return str(target), (
-        f"Fertig: {target.name} · WAV 48 kHz. "
-        "Instrumental ist bei der öffentlichen 3B-Version experimentell."
-    )
-
-
-with gr.Blocks(title="HeartMuLa 3B – Athena Test") as demo:
-    gr.Markdown(
-        "# HeartMuLa 3B – Athena Test\n"
-        "Offizielles öffentliches 3B-Modell. HeartMuLa läuft auf der RTX 5080, "
-        "HeartCodec verlustarm in FP32 auf der RTX 3060. "
-        "Referenzaudio wird von dieser Version noch nicht unterstützt."
-    )
-    tags = gr.Textbox(
-        label="Stil und Instrumente (Komma-getrennte Tags)",
-        value="synthwave,retrowave,1980s,melodic,nostalgic,arpeggiated synthesizer,drum machine,atmospheric,cinematic",
-        lines=3,
-    )
-    lyrics = gr.Textbox(
-        label="Liedtext mit Abschnitten wie [Verse], [Chorus], [Bridge]",
-        lines=14,
-        placeholder="[Verse]\n...\n\n[Chorus]\n...",
-    )
-    instrumental = gr.Checkbox(label="Instrumental (experimentell)", value=True)
-    duration = gr.Slider(20, 240, value=60, step=5, label="Maximale Dauer in Sekunden")
-    with gr.Accordion("Sampling – offizielle Standardwerte", open=False):
-        topk = gr.Slider(1, 200, value=50, step=1, label="Top-k")
-        temperature = gr.Slider(0.1, 2.0, value=1.0, step=0.05, label="Temperatur")
-        cfg_scale = gr.Slider(1.0, 4.0, value=1.5, step=0.1, label="CFG")
-    run = gr.Button("Musik erzeugen", variant="primary")
-    audio = gr.Audio(label="Ergebnis", type="filepath")
-    status = gr.Textbox(label="Status", interactive=False)
-    run.click(
-        generate,
-        inputs=[tags, lyrics, instrumental, duration, topk, temperature, cfg_scale],
-        outputs=[audio, status],
-    )
-
-demo.queue(default_concurrency_limit=1, max_size=4)
-
-api = FastAPI()
-
-
-@api.get("/healthz")
-def healthz():
-    return {
-        "ready": pipeline is not None,
-        "error": load_error or None,
-        "model": "HeartMuLa-oss-3B-happy-new-year",
-        "codec": "HeartCodec-oss-20260123",
-        "mula_device": MULA_DEVICE,
-        "codec_device": CODEC_DEVICE,
-    }
-
-
-api = gr.mount_gradio_app(api, demo, path="/")
-
-if __name__ == "__main__":
-    load_pipeline()
-    uvicorn.run(api, host="0.0.0.0", port=7860)
@@ -1,39 +0,0 @@
-services:
-  heartmula-test:
-    build:
-      context: .
-      args:
-        HEARTLIB_COMMIT: 3783bdb8441f2c298b1e64c8651173aac200361c
-    image: mike-ai/heartmula:3b-3783bdb
-    container_name: mike-ai-heartmula-test
-    restart: "no"
-    environment:
-      NVIDIA_VISIBLE_DEVICES: "GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe,GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b"
-      NVIDIA_DRIVER_CAPABILITIES: compute,utility
-      HEARTMULA_MULA_DEVICE: cuda:0
-      HEARTMULA_CODEC_DEVICE: cuda:1
-    volumes:
-      - /data/models/heartmula:/models:ro
-      - /data/music/heartmula:/output
-    ports:
-      - "127.0.0.1:7863:7860"
-    networks:
-      - frontend
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: all
-              capabilities: [gpu]
-    healthcheck:
-      test: ["CMD", "curl", "-fsS", "http://127.0.0.1:7860/healthz"]
-      interval: 15s
-      timeout: 5s
-      retries: 20
-      start_period: 180s
-
-networks:
-  frontend:
-    external: true
-    name: mike-ai_frontend
@@ -0,0 +1,17 @@
+FROM python:3.12-slim-bookworm
+
+ARG YUE2_COMMIT=9c6c4b349be978b06a9d0d958471a07a6cdeff4d
+
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends ca-certificates git libsndfile1 \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN git clone https://github.com/multimodal-art-projection/YuE.git /opt/yue2 \
+    && git -C /opt/yue2 checkout "${YUE2_COMMIT}" \
+    && python -m pip install --no-cache-dir /opt/yue2
+
+WORKDIR /workspace
+ENV PYTHONUNBUFFERED=1 \
+    YUE2_KIT=/workspace
+
+ENTRYPOINT ["yue2"]
@@ -0,0 +1,52 @@
+# YuE2 3B isolated quality test
+
+Prepared, non-starting evaluation of `m-a-p/YuE2-3B` with the standard
+`m-a-p/YuE2-Vae` listening decoder. The source is pinned to the official
+`yue2-v0.1.6` commit `9c6c4b349be978b06a9d0d958471a07a6cdeff4d`.
+
+Preparation on Athena is complete. The model and VAE files were checked
+against their published `weights_manifest.json` SHA-256 values. The Docker
+image is built, but no YuE2 container has been created or started.
+
+## Safety and isolation
+
+- This experiment is not part of the profile controller or dashboard.
+- The Compose service uses the `manual` profile, has no restart policy and
+  cannot start through an ordinary `docker compose up`.
+- Only the RTX 5080 is exposed to the container.
+- Building and downloading do not load the model or use a GPU.
+- Do not start it while another Athena GPU job is active.
+
+## Persistent files
+
+```text
+/data/models/yue2/
+├── YuE2-3B/
+└── YuE2-Vae/
+
+/data/music/yue2/
+```
+
+The initial control request is a true empty-lyrics instrumental request. No
+invented `[Instrumental]` lyrics marker is used.
+
+## Manual test (only after GPU availability was checked)
+
+From `/opt/mike-ai/yue2-3b` on Athena:
+
+```sh
+docker compose --profile manual run --rm yue2-test generate \
+  --offline \
+  --device cuda:0 \
+  --budget 16 \
+  --request /workspace/requests/instrumental-synthwave.json \
+  --output /workspace/runs
+```
+
+Start with the official unquantized BF16 path. If and only if this fails from
+VRAM pressure, repeat with `--quantization fp8 --offload-ar`; keep the outputs
+separate because that is a different inference configuration.
+
+YuE2 is newly released and officially specifies a 24-GB BF16 GPU. Readiness of
+this image and the downloaded weights is not evidence that the 16-GB RTX 5080
+run will fit or that its audio quality is acceptable.
@@ -0,0 +1,23 @@
+services:
+  yue2-test:
+    profiles: ["manual"]
+    build:
+      context: .
+      args:
+        YUE2_COMMIT: 9c6c4b349be978b06a9d0d958471a07a6cdeff4d
+    image: mike-ai/yue2:3b-0.1.6
+    restart: "no"
+    environment:
+      NVIDIA_VISIBLE_DEVICES: "GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe"
+      NVIDIA_DRIVER_CAPABILITIES: compute,utility
+    volumes:
+      - /data/models/yue2:/workspace/models:ro
+      - /data/music/yue2:/workspace/runs
+      - ./requests:/workspace/requests:ro
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: ["GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe"]
+              capabilities: [gpu]
@@ -0,0 +1,7 @@
+{
+  "id": "instrumental_synthwave_control",
+  "style": "Instrumental, synthwave, synth-pop, energetic, memorable lead melody, arpeggiated synthesizer, analog synthesizer, drum machine, driving bass, 118 BPM, no vocals",
+  "lyrics": "",
+  "cot": "full",
+  "seed": 831001
+}