Simpler: let the ZeroGPU allocator queue GPU calls (concurrency_limit=None), parallel CPU events

Per review: no Gradio-level GPU gate at all. Generate events get concurrency_limit=None — the ZeroGPU allocator queues GPU allocation per call with its own 'Waiting for a GPU' UI, and the composer LLM call at the start of simple_generate now starts the moment the user clicks. Explicit None matters: unset falls back to Gradio's default of 1 per function. CPU events (assist 8, video 4, examples None) keep their bumps since the default serialized them across users. The compose/sing split from the previous commit is dropped — not needed under this model.

app.py

@@ -1533,21 +1533,19 @@ def compose_assist(raw_state, duration):
     return state, "Lyrics & structured prompt ready — review and tweak them, then press Generate."
 
 
-def simple_compose(state, duration):
-    # Composing is a plain LLM API call, so it runs OUTSIDE the GPU queue: it starts the moment the user
-    # clicks instead of waiting behind every queued song. The singing step chains after it on the GPU queue.
+def simple_generate(state, duration, seed, randomize_seed, headroom, steps, guidance):
+    # One event so the output components engage (spinner) from the first click, through composing and singing.
     state = _normalize_state(state)
     description = _composed_description(state)
     title = state["title"] or state["description"]
-    yield gr.skip(), "writing lyrics & structured prompt...", gr.skip(), title
+    yield gr.skip(), "writing lyrics & structured prompt...", gr.skip(), gr.skip(), gr.skip(), title
     lyr, gm, vd, arr = compose_song(description, duration)
     state.update(lyrics=lyr, global_meta=gm, vocals=vd, arrangement=arr)
-    yield (
-        {"cmd": "status", "text": "Lyrics ready — waiting for a GPU slot..."},
-        "lyrics ready — waiting for a GPU slot...",
-        state,
-        gr.skip(),
-    )
+    yield {"cmd": "status", "text": "Lyrics ready — acquiring ZeroGPU..."}, "lyrics ready — acquiring ZeroGPU...", gr.skip(), gr.skip(), state, gr.skip()
+    for audio, status, wav, used_seed in generate(
+        description, lyr, gm, vd, arr, duration, seed, randomize_seed, headroom, steps, guidance
+    ):
+        yield audio, status, wav, used_seed, gr.skip(), gr.skip()
 
 
 def studio_generate(state, duration, seed, randomize_seed, headroom, steps, guidance):
@@ -1620,15 +1618,10 @@ with gr.Blocks(theme=gr.themes.Citrus(), css=CSS) as demo:
 
     _knobs = [duration, seed, randomize_seed, headroom, steps, guidance]
 
-    ev_compose = composer.submit(lambda: ({"cmd": "reset", "loader": True, "status": "Writing lyrics & structured prompt with MiniMax-M3...", "nonce": random.random()}, None), None, [player, video_out]).then(
-        simple_compose, [composer, duration],
-        [player, stats, composer, video_title],
-        concurrency_limit=8, show_progress="minimal",
-    )
-    ev_simple = ev_compose.success(
-        studio_generate, [composer] + _knobs,
-        [player, stats, wav_state, seed, video_title],
-        concurrency_limit=1, concurrency_id="gpu", show_progress="minimal",
+    ev_simple = composer.submit(lambda: ({"cmd": "reset", "loader": True, "status": "Writing lyrics & structured prompt with MiniMax-M3...", "nonce": random.random()}, None), None, [player, video_out]).then(
+        simple_generate, [composer] + _knobs,
+        [player, stats, wav_state, seed, composer, video_title],
+        concurrency_limit=None, show_progress="minimal",
     )
     ev_simple.then(render_video, [wav_state, video_title], video_out, concurrency_limit=4).then(
         lambda s: s.replace(" — rendering share video...", " — share video ready."), stats, stats
@@ -1637,7 +1630,7 @@ with gr.Blocks(theme=gr.themes.Citrus(), css=CSS) as demo:
     ev_studio = composer.click(lambda: ({"cmd": "reset", "loader": True, "status": "Acquiring ZeroGPU...", "nonce": random.random()}, "", None), None, [player, stats, video_out]).then(
         studio_generate, [composer] + _knobs,
         [player, stats, wav_state, seed, video_title],
-        concurrency_limit=1, concurrency_id="gpu", show_progress="minimal",
+        concurrency_limit=None, show_progress="minimal",
     )
     ev_studio.then(render_video, [wav_state, video_title], video_out, concurrency_limit=4).then(
         lambda s: s.replace(" — rendering share video...", " — share video ready."), stats, stats
@@ -1645,7 +1638,7 @@ with gr.Blocks(theme=gr.themes.Citrus(), css=CSS) as demo:
 
     player.stop(
         lambda: "stopped — kept the part that was already streamed.", None, stats,
-        cancels=[ev_compose, ev_simple, ev_studio], show_progress="hidden",
+        cancels=[ev_simple, ev_studio], show_progress="hidden",
     )
 
     composer.edit(compose_assist, [composer, duration], [composer, stats], concurrency_limit=8, show_progress="minimal")