Seems like we're getting CUDA error: an illegal memory access was encountered
<|im_start|>user

Caption

dark trap, 808u

Lyric

<|im_end|>
<|im_start|>assistant

Generating: 0%| | 0/1 [00:00<?, ?steps/s]
Generating: 0%| | 0/1 [00:00<?, ?steps/s]
2026-01-30 22:46:11.497 | INFO | acestep.inference:generate_music:377 - [generate_music] LLM usage decision: thinking=True, use_cot_caption=True, use_cot_language=True, use_cot_metas=True, need_lm_for_cot=True, llm_initialized=True, use_lm=True
2026-01-30 22:46:11.497 | INFO | acestep.inference:generate_music:435 - LM chunk 1/1 (infer_type=llm_dit) (size: 2, seeds: [3550754306, 2083999114])
2026-01-30 22:46:11.497 | INFO | acestep.llm_inference:generate_with_stop_condition:897 - Batch Phase 1: Generating CoT metadata (once for all items)...
2026-01-30 22:46:11.500 | INFO | acestep.llm_inference:generate_with_stop_condition:905 - generate_with_stop_condition: formatted_prompt=<|im_start|>system

Instruction

Generate audio semantic tokens based on the given conditions:

<|im_end|>
<|im_start|>user

Caption

R&B with smooth vocal-style melodies, warm synth chords, grooving basslines, crisp drums, and soulful harmonies blending modern rhythm with classic soul emotion.

Lyric

[Intro R&B with lush synth pads, mellow chords, and subtle rhythmic groove]

[Instrumental R&B with flowing melodies, warm harmonies, and smooth groove-driven rhythms]
<|im_end|>
<|im_start|>assistant

Generating: 0%| | 0/1 [00:00<?, ?steps/s]
Generating: 0%| | 0/1 [00:00<?, ?steps/s]
2026-01-30 22:46:29.095 | INFO | acestep.llm_inference:create_sample_from_query:1561 - Creating sample from query: Rap... (instrumental=[], vocal_language=unknown)
2026-01-30 22:46:29.097 | DEBUG | acestep.llm_inference:create_sample_from_query:1568 - Formatted prompt for inspiration: <|im_start|>system

Instruction

Expand the user's input into a more detailed and specific musical description:

<|im_end|>
<|im_start|>user
Rap

instrumental: false<|im_end|>
<|im_start|>assistant

2026-01-30 22:46:29.097 | DEBUG | acestep.constrained_logits_processor:set_target_duration:1226 - Target duration cleared, no duration constraint
2026-01-30 22:46:29.097 | DEBUG | acestep.constrained_logits_processor:set_user_metadata:424 - No user-provided metadata, all fields will be generated
Generating: 0%| | 0/1 [00:00<?, ?steps/s]
Generating: 0%| | 0/1 [00:00<?, ?steps/s]
Traceback (most recent call last):
File "/home/user/.local/lib/python3.11/site-packages/gradio/queueing.py", line 766, in process_events
response = await route_utils.call_process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/gradio/route_utils.py", line 355, in call_process_api
output = await app.get_blocks().process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/gradio/blocks.py", line 2147, in process_api
result = await self.call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/gradio/blocks.py", line 1641, in call_function
prediction = await utils.async_iteration(iterator)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/gradio/utils.py", line 859, in async_iteration
return await anext(iterator)
^^^^^^^^^^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/gradio/utils.py", line 850, in __anext__
return await anyio.to_thread.run_sync(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/anyio/to_thread.py", line 63, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 2502, in run_sync_in_worker_thread
return await future
^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 986, in run
result = context.run(func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/gradio/utils.py", line 833, in run_sync_iterator_async
return next(iterator)
^^^^^^^^^^^^^^
File "/home/user/.local/lib/python3.11/site-packages/gradio/utils.py", line 1017, in gen_wrapper
response = next(iterator)
^^^^^^^^^^^^^^
File "/home/user/app/acestep/gradio_ui/events/__init__.py", line 671, in generation_wrapper
raise gr.Error(f"Failed to create sample: {result.status_message}")
gradio.exceptions.Error: "Failed to create sample: ❌ Error generating from formatted prompt: CUDA error: an illegal memory access was encountered\nSearch for cudaErrorIllegalAddress' in https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html for more information.\nCUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.\nFor debugging consider passing CUDA_LAUNCH_BLOCKING=1\nCompile with TORCH_USE_CUDA_DSA` to enable device-side assertions.\n"
2026-01-30 22:48:25.567 | INFO | acestep.inference:generate_music:377 - [generate_music] LLM usage decision: thinking=True, use_cot_caption=True, use_cot_language=True, use_cot_metas=True, need_lm_for_cot=True, llm_initialized=True, use_lm=True
2026-01-30 22:48:25.567 | INFO | acestep.inference:generate_music:435 - LM chunk 1/1 (infer_type=llm_dit) (size: 2, seeds: [1396977744, 3121800500])
2026-01-30 22:48:25.567 | INFO | acestep.llm_inference:generate_with_stop_condition:897 - Batch Phase 1: Generating CoT metadata (once for all items)...
2026-01-30 22:48:25.569 | INFO | acestep.llm_inference:generate_with_stop_condition:905 - generate_with_stop_condition: formatted_prompt=<|im_start|>system

Instruction

Generate audio semantic tokens based on the given conditions:

<|im_end|>