ace-step-ui
ace-step-ui copied to clipboard
Published
2 months ago
•
fspecii
fspecii
Generation failed. Please try again.: No audio files generated
Hi, I'm using ACE-Step through Pinokio on Windows with an NVIDIA GTX 1660 Super (6GB VRAM), and I'm running into CUDA memory issues during generation.
Log:
Microsoft Windows [Version 10.0.26200.8246]
(c) Microsoft Corporation. Wszelkie prawa zastrzeżone.
C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Scripts\activate C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env && acestep --port 42003 --enable-api --backend pt --server-name 127.0.0.1
Loaded configuration from C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\.env.example (fallback)
Skipping import of cpp extensions due to incompatible torch version 2.7.1+cu128 for torchao version 0.15.0 Please see https://github.com/pytorch/ao/issues/2919 for more info
W0428 19:33:15.551000 21420 Lib\site-packages\torch\distributed\elastic\multiprocessing\redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs.
2026-04-28 19:33:18.359 | WARNING | acestep.training.trainer:<module>:40 - bitsandbytes not installed. Using standard AdamW.
2026-04-28 19:33:21.697 | INFO | acestep.gpu_config:get_gpu_memory_gb:578 - CUDA GPU detected: NVIDIA GeForce GTX 1660 SUPER (6.0 GB)
============================================================
GPU Configuration Detected:
============================================================
Microsoft Windows [Version 10.0.26200.8246]
(c) Microsoft Corporation. Wszelkie prawa zastrzeżone.
C:\pinokio\api\ace-step-ui.pinokio.git\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base && npm run dev -- --host 127.0.0.1 --port 42004 --strictPort
> [email protected] dev
> vite --host 127.0.0.1 --port 42004 --strictPort
Microsoft Windows [Version 10.0.26200.8246]
(c) Microsoft Corporation. Wszelkie prawa zastrzeżone.
C:\pinokio\api\ace-step-ui.pinokio.git\app\server>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base && npm run dev
> [email protected] dev
> tsx watch src/index.ts
Running SQLite database migrations...
Migrations completed successfully!
██ Detached from Shell 6913ac96-134f-4e01-afd4-72948b1fb8df
ACE-Step UI Server running on http://localhost:3001
===================================================
# input.event
[
"ACE-Step UI Server running"
]
===================================================
Environment: development
ACE-Step API: http://127.0.0.1:42003
LAN access: http://192.168.1.3:3001
LAN access: http://172.25.64.1:3001
Initializing local storage provider
[Gradio] Connected to http://127.0.0.1:42003
Job job_1777397675540_3kfy6mq: Queued at position 1
Job job_1777397675540_3kfy6mq: Using Gradio /generation_wrapper {
prompt: 'classic Motown soul with rich brass section and dr',
duration: undefined,
batchSize: 1
}
Traceback (most recent call last):
File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\gradio\queueing.py", line 766, in process_events
response = await route_utils.call_process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\gradio\route_utils.py", line 355, in call_process_api
output = await app.get_blocks().process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\gradio\blocks.py", line 2143, in process_api
inputs = await self.preprocess_data(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\gradio\blocks.py", line 1790, in preprocess_data
processed_value = block.preprocess(inputs_cached)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\gradio\components\slider.py", line 155, in preprocess
Number.raise_if_out_of_bounds(payload, self.minimum, self.maximum)
File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\gradio\components\number.py", line 136, in raise_if_out_of_bounds
raise Error(f"Value {num} is greater than maximum value {maximum}.")
Job job_1777397675540_3kfy6mq: Gradio generation failed, trying Python spawn fallback {
type: 'status',
endpoint: '/generation_wrapper',
fn_index: 121,
time: 2026-04-28T17:34:35.692Z,
original_msg: undefined,
queue: true,
title: 'Error',
message: 'Value 3 is greater than maximum value 1.0.',
visible: true,
duration: 10,
stage: 'error',
code: undefined,
success: false
}
Job job_1777397675540_3kfy6mq: Using Python spawn (Gradio not available) {
prompt: 'classic Motown soul with rich brass section and dr',
lyricsPreview: '',
duration: undefined,
batchSize: 1
}
[ACE-Step] Skipping import of cpp extensions due to incompatible torch version 2.7.1+cu128 for torchao version 0.15.0 Please see https://github.com/pytorch/ao/issues/2919 for more info
[ACE-Step] W0428 19:34:48.332000 20172 env\Lib\site-packages\torch\distributed\elastic\multiprocessing\redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs.
[ACE-Step] 2026-04-28 19:34:51.193 | WARNING | acestep.training.trainer:<module>:40 - bitsandbytes not installed. Using standard AdamW.
[ACE-Step] 2026-04-28 19:34:51.243 | INFO | acestep.gpu_config:get_gpu_memory_gb:578 - CUDA GPU detected: NVIDIA GeForce GTX 1660 SUPER (6.0 GB)
[ACE-Step] 2026-04-28 19:34:51.243 | INFO | acestep.core.generation.handler.init_service_orchestrator:initialize_service:96 - [initialize_service] Pre-Ampere CUDA detected: using float16 instead of bfloat16.
[ACE-Step] 2026-04-28 19:34:51.406 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:151 - [initialize_service] Pre-Ampere CUDA detected: using eager attention for float16 numerical stability.
[ACE-Step] 2026-04-28 19:34:51.406 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:174 - [initialize_service] Attempting to load model with attention implementation: eager
[ACE-Step] 2026-04-28 19:35:00.703 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:200 - [initialize_service] Keeping main model on cuda (persistent)
[ACE-Step] 2026-04-28 19:35:06.296 | INFO | acestep.inference:generate_music:443 - [generate_music] LLM usage decision: thinking=False, use_cot_caption=True, use_cot_language=True, use_cot_metas=True, need_lm_for_cot=True, llm_initialized=False, use_lm=False
[ACE-Step] 2026-04-28 19:35:06.297 | INFO | acestep.core.generation.handler.generate_music:generate_music:278 - [generate_music] Turbo model detected: overriding guidance_scale 9.0 -> 1.0 (turbo does not use CFG).
[ACE-Step] 2026-04-28 19:35:06.297 | INFO | acestep.core.generation.handler.generate_music:generate_music:293 - [generate_music] Starting generation...
[ACE-Step] 2026-04-28 19:35:06.297 | INFO | acestep.core.generation.handler.generate_music:generate_music:296 - [generate_music] Preparing inputs...
[ACE-Step] 2026-04-28 19:35:06.305 | DEBUG | acestep.core.generation.handler.generate_music:_vram_preflight_check:132 - [generate_music] VRAM pre-flight: skipping check (offload_to_cpu=True, models loaded one-at-a-time)
[ACE-Step] 2026-04-28 19:35:06.322 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:41 - [_load_model_context] Loading vae to cuda (RSS: 0 MB)
[ACE-Step] 2026-04-28 19:35:06.700 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:58 - [_load_model_context] Loaded vae to cuda in 0.1944s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-04-28 19:35:06.753 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:67 - [_load_model_context] Offloading vae to CPU (RSS: 0 MB)
[ACE-Step] 2026-04-28 19:35:07.342 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:83 - [_load_model_context] Offloaded vae to CPU in 0.3605s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-04-28 19:35:07.377 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 -
[ACE-Step] ======================================================================
[ACE-Step] 2026-04-28 19:35:07.377 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - \U0001f50d [DEBUG] DiT TEXT ENCODER INPUT (Inference)
[ACE-Step] 2026-04-28 19:35:07.377 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ======================================================================
[ACE-Step] 2026-04-28 19:35:07.377 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:122 - text_prompt:
[ACE-Step] # Instruction
[ACE-Step] Fill the audio semantic mask based on the given conditions:
[ACE-Step] # Caption
[ACE-Step] classic Motown soul with rich brass section and driving rhythm
[ACE-Step] # Metas
[ACE-Step] - bpm: N/A
[ACE-Step] - timesignature: N/A
[ACE-Step] - keyscale: N/A
[ACE-Step] - duration: 60 seconds
[ACE-Step] <|endoftext|>
[ACE-Step] 2026-04-28 19:35:07.377 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ======================================================================
[ACE-Step] 2026-04-28 19:35:07.377 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:124 - lyrics_text:
[ACE-Step] # Languages
[ACE-Step] en
[ACE-Step] # Lyric
[ACE-Step] <|endoftext|>
[ACE-Step] 2026-04-28 19:35:07.378 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ======================================================================
[ACE-Step] 2026-04-28 19:35:07.399 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:41 - [_load_model_context] Loading vae to cuda (RSS: 0 MB)
[ACE-Step] 2026-04-28 19:35:07.743 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:58 - [_load_model_context] Loaded vae to cuda in 0.1562s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-04-28 19:35:07.768 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:67 - [_load_model_context] Offloading vae to CPU (RSS: 0 MB)
[ACE-Step] 2026-04-28 19:35:08.189 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:83 - [_load_model_context] Offloaded vae to CPU in 0.2434s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-04-28 19:35:08.191 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings...
[ACE-Step] 2026-04-28 19:35:08.191 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:41 - [_load_model_context] Loading text_encoder to cuda (RSS: 0 MB)
[ACE-Step] 2026-04-28 19:35:08.771 | ERROR | acestep.core.generation.handler.generate_music:generate_music:445 - [generate_music] Generation failed
[ACE-Step] Traceback (most recent call last):
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\server\scripts\simple_generate.py", line 291, in <module>
[ACE-Step] main()
[ACE-Step] -> <function main at 0x00000150BC6BCD60>
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\server\scripts\simple_generate.py", line 228, in main
[ACE-Step] result = generate(
[ACE-Step] -> <function generate at 0x00000150BC6AA700>
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\server\scripts\simple_generate.py", line 155, in generate
[ACE-Step] result = generate_music(handler, llm_handler, params, config, save_dir=output_dir)
[ACE-Step] | | | | | -> 'C:\\pinokio\\api\\ace-step-ui.pinokio.git\\app\\ACE-Step-1.5\\output\\job_1777397675540_3kfy6mq'
[ACE-Step] | | | | -> GenerationConfig(batch_size=1, allow_lm_batch=False, use_random_seed=True, seeds=None, lm_batch_chunk_size=8, constrained_dec...
[ACE-Step] | | | -> GenerationParams(task_type='text2music', instruction='Fill the audio semantic mask based on the given conditions:', reference...
[ACE-Step] | | -> <acestep.llm_inference.LLMHandler object at 0x00000150BC6DCA50>
[ACE-Step] | -> <acestep.handler.AceStepHandler object at 0x00000150BBBC1050>
[ACE-Step] -> <function generate_music at 0x00000150BC6BC4A0>
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\acestep\inference.py", line 683, in generate_music
[ACE-Step] result = dit_handler.generate_music(**filtered_generate_kwargs)
[ACE-Step] | | -> {'captions': 'classic Motown soul with rich brass section and driving rhythm', 'global_caption': '', 'lyrics': '', 'bpm': Non...
[ACE-Step] | -> <function GenerateMusicMixin.generate_music at 0x0000015088745B20>
[ACE-Step] -> <acestep.handler.AceStepHandler object at 0x00000150BBBC1050>
[ACE-Step] > File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\acestep\core\generation\handler\generate_music.py", line 358, in generate_music
[ACE-Step] service_run = self._run_generate_music_service_with_progress(
[ACE-Step] | -> <function GenerateMusicExecuteMixin._run_generate_music_service_with_progress at 0x0000015088746020>
[ACE-Step] -> <acestep.handler.AceStepHandler object at 0x00000150BBBC1050>
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\acestep\core\generation\handler\generate_music_execute.py", line 142, in _run_generate_music_service_with_progress
[ACE-Step] raise _error["exc"]
[ACE-Step] -> {'exc': OutOfMemoryError('CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacity of 6.00 GiB of which 0 ...
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\acestep\core\generation\handler\generate_music_execute.py", line 70, in _service_target
[ACE-Step] _result["outputs"] = self.service_generate(
[ACE-Step] | | -> <function ServiceGenerateMixin.service_generate at 0x00000150BC64DB20>
[ACE-Step] | -> <acestep.handler.AceStepHandler object at 0x00000150BBBC1050>
[ACE-Step] -> {}
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
[ACE-Step] return func(*args, **kwargs)
[ACE-Step] | | -> {'captions': ['classic Motown soul with rich brass section and driving rhythm'], 'global_captions': [''], 'lyrics': [''], 'me...
[ACE-Step] | -> (<acestep.handler.AceStepHandler object at 0x00000150BBBC1050>,)
[ACE-Step] -> <function ServiceGenerateMixin.service_generate at 0x00000150BC64DA80>
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\acestep\core\generation\handler\service_generate.py", line 146, in service_generate
[ACE-Step] payload = self._unpack_service_processed_data(self.preprocess_batch(batch))
[ACE-Step] | | | | -> {'keys': None, 'target_wavs': tensor([[[0., 0., 0., ..., 0., 0., 0.],
[ACE-Step] | | | | [0., 0., 0., ..., 0., 0., 0.]]], device='cud...
[ACE-Step] | | | -> <function ConditioningEmbedMixin.preprocess_batch at 0x00000150887440E0>
[ACE-Step] | | -> <acestep.handler.AceStepHandler object at 0x00000150BBBC1050>
[ACE-Step] | -> <function ServiceGenerateExecuteMixin._unpack_service_processed_data at 0x00000150BC64D300>
[ACE-Step] -> <acestep.handler.AceStepHandler object at 0x00000150BBBC1050>
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\acestep\core\generation\handler\conditioning_embed.py", line 111, in preprocess_batch
[ACE-Step] with self._load_model_context("text_encoder"):
[ACE-Step] | -> <function InitServiceOffloadContextMixin._load_model_context at 0x000001508877D940>
[ACE-Step] -> <acestep.handler.AceStepHandler object at 0x00000150BBBC1050>
[ACE-Step] File "C:\Users\HRudo\AppData\Roaming\uv\python\cpython-3.11-windows-x86_64-none\Lib\contextlib.py", line 137, in __enter__
[ACE-Step] return next(self.gen)
[ACE-Step] | -> <generator object InitServiceOffloadContextMixin._load_model_context at 0x00000150D9C38600>
[ACE-Step] -> <contextlib._GeneratorContextManager object at 0x00000150D9BE4510>
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\acestep\core\generation\handler\init_service_offload_context.py", line 47, in _load_model_context
[ACE-Step] self._recursive_to_device(model, self.device, self.dtype)
[ACE-Step] | | | | | | -> torch.float16
[ACE-Step] | | | | | -> <acestep.handler.AceStepHandler object at 0x00000150BBBC1050>
[ACE-Step] | | | | -> 'cuda'
[ACE-Step] | | | -> <acestep.handler.AceStepHandler object at 0x00000150BBBC1050>
[ACE-Step] | | -> Qwen3Model(
[ACE-Step] | | (embed_tokens): Embedding(151669, 1024)
[ACE-Step] | | (layers): ModuleList(
[ACE-Step] | | (0-27): 28 x Qwen3DecoderLayer(
[ACE-Step] | | (self...
[ACE-Step] | -> <function InitServiceMemoryTransferMixin._recursive_to_device at 0x000001508877D760>
[ACE-Step] -> <acestep.handler.AceStepHandler object at 0x00000150BBBC1050>
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\acestep\core\generation\handler\init_service_memory_transfer.py", line 85, in _recursive_to_device
[ACE-Step] model.to(device=target_device, dtype=dtype)
[ACE-Step] | | | -> torch.float16
[ACE-Step] | | -> device(type='cuda')
[ACE-Step] | -> <function Module.to at 0x00000150B8214400>
[ACE-Step] -> Qwen3Model(
[ACE-Step] (embed_tokens): Embedding(151669, 1024)
[ACE-Step] (layers): ModuleList(
[ACE-Step] (0-27): 28 x Qwen3DecoderLayer(
[ACE-Step] (self...
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\transformers\modeling_utils.py", line 4343, in to
[ACE-Step] return super().to(*args, **kwargs)
[ACE-Step] | -> {'device': device(type='cuda'), 'dtype': torch.float16}
[ACE-Step] -> ()
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\torch\nn\modules\module.py", line 1355, in to
[ACE-Step] return self._apply(convert)
[ACE-Step] | | -> <function Module.to.<locals>.convert at 0x000001508A7BBE20>
[ACE-Step] | -> <function Module._apply at 0x00000150FF898EA0>
[ACE-Step] -> Qwen3Model(
[ACE-Step] (embed_tokens): Embedding(151669, 1024)
[ACE-Step] (layers): ModuleList(
[ACE-Step] (0-27): 28 x Qwen3DecoderLayer(
[ACE-Step] (self...
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\torch\nn\modules\module.py", line 915, in _apply
[ACE-Step] module._apply(fn)
[ACE-Step] | | -> <function Module.to.<locals>.convert at 0x000001508A7BBE20>
[ACE-Step] | -> <function Module._apply at 0x00000150FF898EA0>
[ACE-Step] -> ModuleList(
[ACE-Step] (0-27): 28 x Qwen3DecoderLayer(
[ACE-Step] (self_attn): Qwen3Attention(
[ACE-Step] (q_proj): Linear(in_features=1024, out_f...
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\torch\nn\modules\module.py", line 915, in _apply
[ACE-Step] module._apply(fn)
[ACE-Step] | | -> <function Module.to.<locals>.convert at 0x000001508A7BBE20>
[ACE-Step] | -> <function Module._apply at 0x00000150FF898EA0>
[ACE-Step] -> Qwen3DecoderLayer(
[ACE-Step] (self_attn): Qwen3Attention(
[ACE-Step] (q_proj): Linear(in_features=1024, out_features=2048, bias=False)
[ACE-Step] (...
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\torch\nn\modules\module.py", line 915, in _apply
[ACE-Step] module._apply(fn)
[ACE-Step] | | -> <function Module.to.<locals>.convert at 0x000001508A7BBE20>
[ACE-Step] | -> <function Module._apply at 0x00000150FF898EA0>
[ACE-Step] -> Qwen3MLP(
[ACE-Step] (gate_proj): Linear(in_features=1024, out_features=3072, bias=False)
[ACE-Step] (up_proj): Linear(in_features=1024, out_fe...
[ACE-Step] [Previous line repeated 1 more time]
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\torch\nn\modules\module.py", line 942, in _apply
[ACE-Step] param_applied = fn(param)
[ACE-Step] | -> Parameter containing:
[ACE-Step] | tensor([[-0.0317, 0.0009, -0.0003, ..., -0.0129, 0.0253, -0.0004],
[ACE-Step] | [-0.0054, -0.0003, 0.014...
[ACE-Step] -> <function Module.to.<locals>.convert at 0x000001508A7BBE20>
[ACE-Step] File "C:\pinokio\api\ace-step-ui.pinokio.git\app\ACE-Step-1.5\env\Lib\site-packages\torch\nn\modules\module.py", line 1341, in convert
[ACE-Step] return t.to(
[ACE-Step] | -> <method 'to' of 'torch._C.TensorBase' objects>
[ACE-Step] -> Parameter containing:
[ACE-Step] tensor([[-0.0317, 0.0009, -0.0003, ..., -0.0129, 0.0253, -0.0004],
[ACE-Step] [-0.0054, -0.0003, 0.014...
[ACE-Step] torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacity of 6.00 GiB of which 0 bytes is free. Of the allocated memory 5.31 GiB is allocated by PyTorch, and 6.91 MiB is reserved by PyTorch but unallocated. If reser rved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See document tation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
Job job_1777397675540_3kfy6mq: Generation failed Error: No audio files generated
at processGenerationViaPython (C:\pinokio\api\ace-step-ui.pinokio.git\app\server\src\services\acestep.ts:727:13)
at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
at async processGeneration (C:\pinokio\api\ace-step-ui.pinokio.git\app\server\src\services\acestep.ts:507:3)
at async processQueue (C:\pinokio\api\ace-step-ui.pinokio.git\app\server\src\services\acestep.ts:432:9)
