[Request] Parsed ggml-turbo/request0.json [Request] seed=42 lm_batch=1 synth_batch=1 [Request] caption: An upbeat and anthemic pop-rock track driven by bright, slig... [Request] lyrics: 490 bytes [Request] bpm=83 dur=88 key=G major ts=4 lang=fr [Request] lm: temp=0.85 cfg=2.0 top_p=0.90 top_k=0 [Request] dit: steps=8 guidance=0.0 shift=3.0 [Request] task_type: text2music [Request] solver: euler (stork_substeps=10) [Request] lm_mode: generate [Request] output_format: mp3 [Request] synth_model: acestep-v15-turbo-BF16.gguf [Request] vae: vae-BF16.gguf [Request] audio_codes: (present) [Ace-Synth] Batch: 1 request(s) [Registry] Qwen3-Embedding-0.6B-BF16.gguf -> Text-Enc [Registry] Qwen3-Embedding-0.6B-Q8_0.gguf -> Text-Enc [Registry] acestep-5Hz-lm-0.6B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-0.6B-Q8_0.gguf -> LM [Registry] acestep-5Hz-lm-1.7B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-1.7B-Q8_0.gguf -> LM [Registry] acestep-5Hz-lm-4B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q5_K_M.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q6_K.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q8_0.gguf -> LM [Registry] acestep-v15-base-BF16.gguf -> DiT [Registry] acestep-v15-base-Q4_K_M.gguf -> DiT [Registry] acestep-v15-base-Q5_K_M.gguf -> DiT [Registry] acestep-v15-base-Q6_K.gguf -> DiT [Registry] acestep-v15-base-Q8_0.gguf -> DiT [Registry] acestep-v15-sft-BF16.gguf -> DiT [Registry] acestep-v15-sft-Q4_K_M.gguf -> DiT [Registry] acestep-v15-sft-Q5_K_M.gguf -> DiT [Registry] acestep-v15-sft-Q6_K.gguf -> DiT [Registry] acestep-v15-sft-Q8_0.gguf -> DiT [Registry] acestep-v15-sftturbo50-BF16.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q4_K_M.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q5_K_M.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q6_K.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-BF16.gguf -> DiT [Registry] acestep-v15-turbo-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-continuous-BF16.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-shift1-BF16.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-shift3-BF16.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-base-BF16.gguf -> DiT [Registry] acestep-v15-xl-base-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-base-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-base-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-base-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-sft-BF16.gguf -> DiT [Registry] acestep-v15-xl-sft-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-sft-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-sft-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-sft-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-BF16.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-turbo-BF16.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q8_0.gguf -> DiT [Registry] scragvae-BF16.gguf -> VAE [Registry] vae-BF16.gguf -> VAE [Store] Created (policy=STRICT) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-turbo-BF16.gguf: 678 tensors, data at offset 57024 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-turbo-BF16.gguf: 678 tensors, data at offset 57024 [Synth-Load] Ready: turbo=yes, fa=no, batch_cfg=yes [Resolve-Params] max audio codes across batch: 434 (86.8s @ 5Hz) [Resolve-T] T=2170, S=1085 [Resolve-T] seed=42, steps=8, guidance=1.0, shift=3.0, duration=88.0s [BPE] Loaded from GGUF: 151643 vocab, 151387 merges ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): Device 0: NVIDIA RTX PRO 6000 Blackwell Workstation Edition, compute capability 12.0, VMM: yes, VRAM: 97247 MiB load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = NVIDIA RTX PRO 6000 Blackwell Workstation Edition (NVIDIA) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2 load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] TextEncoder backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/Qwen3-Embedding-0.6B-BF16.gguf: 310 tensors, data at offset 5337568 [Load] TextEncoder: 28L, H=1024, Nh=16/8 [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 310 tensors, 1136.5 MB into backend [Store] Load TextEnc: 276 ms [Debug] text_hidden: [70, 1024] first4: 3.704526 2.436253 0.222853 -13.131872 [Debug] lyric_embed: [167, 1024] first4: 0.029175 0.032227 -0.022339 -0.028809 [Store] Unload TextEnc (1136.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] CondEncoder backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-turbo-BF16.gguf: 678 tensors, data at offset 57024 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 140 tensors, 1160.5 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L), text_proj, null_cond [Store] Load CondEnc: 843 ms [CondEnc] Lyric sliding mask: 167x167, window=128 [CondEnc] Timbre sliding mask: 1x1, window=128 [Encode] Packed: lyric=167 + timbre=1 + text=70 = 238 tokens [Encode-Text Batch0] 70+167 tokens -> enc_S=238, 97.9 ms [Debug] enc_hidden: [238, 2048] first4: 1.758276 -0.049599 -0.132827 0.058514 [Store] Unload CondEnc (1160.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] Detokenizer backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-turbo-BF16.gguf: 678 tensors, data at offset 57024 [WeightCtx] Loaded 30 tensors, 200.3 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 126 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 908.1 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.124172 1.435321 0.310164 -0.624504 [Store] Unload FSQ-Detok (200.3 MB) [Init-Noise Batch0] Philox noise seed=42, [2170, 64] solver=euler [Debug] noise: [2170, 64] first4: 0.194336 2.156250 -0.171875 0.847656 [Debug] context: [2170, 128] first4: -0.124172 1.435321 0.310164 -0.624504 [Init-Noise] Starting: T=2170, S=1085, enc_S=238, steps=8, batch=1 (cover) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] DiT backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-turbo-BF16.gguf: 678 tensors, data at offset 57024 [DiT] Self-attn: Q+K+V fused [DiT] Cross-attn: Q+K+V fused [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 478 tensors, 3007.9 MB into backend [Load] DiT: 24 layers, H=2048, Nh=16/8, D=128 [Store] Load DiT: 1577 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2129 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [12288] first4: 0.260222 -0.161617 -0.097078 0.052346 [Debug] temb: [2048] first4: 0.000077 -0.132559 -0.035432 0.064735 [Debug] temb_t: [2048] first4: 0.001069 0.026790 -0.052756 0.063697 [Debug] temb_r: [2048] first4: -0.000991 -0.159349 0.017324 0.001038 [Debug] sinusoidal_t: [256] first4: 0.562379 0.789627 0.439928 -0.023645 [Debug] sinusoidal_r: [256] first4: 1.000000 1.000000 1.000000 1.000000 [Debug] temb_lin1_t: [2048] first4: -0.049513 -0.051899 -0.014138 -0.038434 [Debug] temb_lin1_r: [2048] first4: -0.013266 -0.018319 -0.016375 0.008532 [Debug] hidden_after_proj_in: [2048, 1085] first4: -1.039860 -0.969668 0.533155 0.446510 [Debug] proj_in_input: [192, 2170] first4: -0.124172 1.435321 0.310164 -0.624504 [Debug] enc_after_cond_emb: [2048, 238] first4: -0.168718 0.814694 0.326832 -0.562843 [Debug] layer0_sa_input: [2048, 1085] first4: -0.719531 -0.764448 -0.047718 0.261790 [Debug] layer0_q_after_rope: [128, 16] first4: -1.541144 -1.045369 0.187089 0.455729 [Debug] layer0_k_after_rope: [128, 8] first4: -0.168718 0.814694 0.326832 -0.562843 [Debug] layer0_sa_output: [2048, 1085] first4: -1.500230 0.170585 -0.354305 0.512672 [Debug] layer0_attn_out: [2048, 1085] first4: -1.541144 -1.045369 0.187089 0.455729 [Debug] layer0_after_self_attn: [2048, 1085] first4: -1.541144 -1.045369 0.187089 0.455729 [Debug] layer0_after_cross_attn: [2048, 1085] first4: -1.598600 -0.822307 -0.294828 0.493505 [Debug] hidden_after_layer0: [2048, 1085] first4: -9.101245 0.570783 52.416466 -0.907659 [Debug] hidden_after_layer6: [2048, 1085] first4: -21.190231 0.074572 33.690300 -4.495945 [Debug] hidden_after_layer12: [2048, 1085] first4: -15.056320 -17.914547 72.452255 28.845539 [Debug] hidden_after_layer18: [2048, 1085] first4: -27.582886 15.800710 60.610252 21.090904 [Debug] hidden_after_layer23: [2048, 1085] first4: -12.761587 45.375771 198.019775 145.498611 [Debug] dit_step0_vt: [2170, 64] first4: 0.022098 1.114333 0.345665 2.377955 [Debug] dit_step0_xt: [2170, 64] first4: 0.193331 2.105598 -0.187587 0.739567 [DiT] Step 1/8 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.235107 1.306051 -0.132166 1.882218 [Debug] dit_step1_xt: [2170, 64] first4: 0.206156 2.034359 -0.180378 0.636901 [DiT] Step 2/8 t=0.955 [Debug] dit_step2_vt: [2170, 64] first4: -0.023448 1.209205 0.106523 2.388911 [Debug] dit_step2_xt: [2170, 64] first4: 0.207719 1.953746 -0.187480 0.477640 [DiT] Step 3/8 t=0.900 [Debug] dit_step3_vt: [2170, 64] first4: 0.245050 1.089456 0.259572 2.637362 [Debug] dit_step3_xt: [2170, 64] first4: 0.187298 1.862958 -0.209111 0.257860 [DiT] Step 4/8 t=0.833 [Debug] dit_step4_vt: [2170, 64] first4: 0.290814 1.012087 0.108243 2.713056 [Debug] dit_step4_xt: [2170, 64] first4: 0.156139 1.754520 -0.220708 -0.032824 [DiT] Step 5/8 t=0.750 [Debug] dit_step5_vt: [2170, 64] first4: 0.266973 0.927089 -0.300413 2.760701 [Debug] dit_step5_xt: [2170, 64] first4: 0.118000 1.622078 -0.177792 -0.427210 [DiT] Step 6/8 t=0.643 [Debug] dit_step6_vt: [2170, 64] first4: 0.172337 0.637162 -0.831558 2.825220 [Debug] dit_step6_xt: [2170, 64] first4: 0.083533 1.494646 -0.011480 -0.992254 [DiT] Step 7/8 t=0.500 [Debug] dit_step7_vt: [2170, 64] first4: -0.007689 0.185485 -1.474427 3.111979 [Debug] dit_x0: [2170, 64] first4: 0.085840 1.439000 0.430848 -1.925848 [DiT] Step 8/8 t=0.300 [DiT-Generate] Total: 18461.3 ms (18461.3 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.085840 1.439000 0.430848 -1.925848 [Store] Unload DiT (3007.9 MB) [GGUF] /mnt/workspace/git/acestep.cpp/models/vae-BF16.gguf: 365 tensors, data at offset 30048 load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] VAE backend: CPU (CPU threads: 16) [VAE] Backend: CPU, Weight buffer: 161.1 MB [VAE] Loaded: 5 blocks, upsample=1920x, F32 activations [Store] Load VAE-Dec: 715 ms [VAE] Tiled decode: 3 tiles (chunk=1024, overlap=64, stride=896) [VAE] Graph: 479 nodes, T_latent=960 [VAE] Upsample factor: 1920.00 (expected ~1920) [VAE] Graph: 479 nodes, T_latent=1024 [VAE] Graph: 479 nodes, T_latent=442 [VAE] Tiled decode done: 3 tiles -> T_audio=4166400 (86.80s @ 48kHz) [VAE-Decode Batch0] Decode: 32249.5 ms [Debug] vae_audio: [2, 4166400] first4: 0.000700 0.001419 0.001187 0.001709 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 512 ms (169.60x realtime), 32 threads [MP3] Wrote ggml-turbo/request00.mp3 [Ace-Synth] All done 2026-07-12 09:12:44.382 | DEBUG | acestep.core.generation.handler.init_service_memory_basic:_apply_malloc_mmap_threshold:50 - [memory] Set M_MMAP_THRESHOLD=131072 for immediate OS reclaim of large frees Skipping import of cpp extensions due to incompatible torch version. Please upgrade to torch >= 2.11.0 (found 2.10.0+cu128). 2026-07-12 09:12:46.452 | WARNING | acestep.training.trainer::40 - bitsandbytes not installed. Using standard AdamW. 2026-07-12 09:12:46.454 | INFO | acestep.gpu_config:get_gpu_memory_gb:578 - CUDA GPU detected: NVIDIA RTX PRO 6000 Blackwell Workstation Edition (95.0 GB) 2026-07-12 09:12:46.554 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:174 - [initialize_service] Attempting to load model with attention implementation: sdpa Unable to import `torchao` Tensor objects. This may affect loading checkpoints serialized with `torchao` 2026-07-12 09:12:48.177 | INFO | acestep.core.generation.handler.generate_music:generate_music:289 - [generate_music] Turbo model detected: overriding guidance_scale 0.0 -> 1.0 (turbo does not use CFG). 2026-07-12 09:12:48.177 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 09:12:48.177 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 09:12:48.177 | INFO | acestep.core.generation.handler.generate_music_request:_prepare_reference_and_source_audio:179 - [generate_music] cover task: no src_audio but audio codes provided, proceeding with codes 2026-07-12 09:12:48.181 | INFO | acestep.core.generation.handler.generate_music:_vram_preflight_check:156 - [generate_music] VRAM pre-flight: 87.83 GB free, ~0.94 GB needed (batch=1, duration=88s, mode=turbo). 2026-07-12 09:12:48.186 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 09:12:48.399 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_precomputed_lm_hints:31 - [generate_music] Decoding audio codes for LM hints for item 0... 2026-07-12 09:12:48.401 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 09:12:48.401 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 09:12:48.401 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 09:12:48.401 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:122 - text_prompt: # Instruction Generate audio semantic tokens based on the given conditions: # Caption An upbeat and anthemic pop-rock track driven by bright, slightly overdriven # Metas - bpm: 83 - timesignature: 4 - keyscale: G major - duration: 88 seconds <|endoftext|> 2026-07-12 09:12:48.401 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 09:12:48.401 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:124 - lyrics_text: # Languages fr # Lyric # Lyric [Intro - Guitar Riff] [Verse 1] Dans le monde des tutos virtuels G ta toise en nouvelle passion Avec Ggendoline et PumbΓ© Γ  midi La communautΓ©, c'est l'unitΓ© Quel joie, une clΓ© [Chorus] Dans le monde des tutos virtuels GΓ’ndoline et PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner [Guitar Solo] [Verse 2] Dans le monde des tutos virtuels GΓ’ndoline, PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner<|endoftext|> 2026-07-12 09:12:48.401 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 09:12:48.408 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 09:12:48.423 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 09:12:48.423 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 09:12:48.450 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)... 2026-07-12 09:12:48.457 | INFO | acestep.models.common.dcw_correction:__init__:98 - [DCW] Active β€” mode=double, scaler=0.0500, high_scaler=0.0200, wavelet='haar' 2026-07-12 09:12:48.544 | WARNING | acestep.models.common.dcw_loader:_try_import:39 - DCW is enabled but 'pytorch_wavelets' is not installed. Install with `pip install pytorch_wavelets PyWavelets` to use Differential Correction in Wavelet domain. Falling back to no-op for this generation. 2026-07-12 09:12:48.781 | INFO | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:42 - [generate_music] Model generation completed. Decoding latents... 2026-07-12 09:12:48.782 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:64 - [generate_music] pred_latents: torch.Size([1, 2170, 64]), dtype=torch.bfloat16 2026-07-12 09:12:48.782 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:65 - [generate_music] time_costs: {'encoder_time_cost': 0.00696253776550293, 'diffusion_time_cost': 0.32336997985839844, 'diffusion_per_step_time_cost': 0.040421247482299805, 'total_time_cost': 0.33033251762390137, 'offload_time_cost': 0.0} 2026-07-12 09:12:48.795 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:127 - [generate_music] Decoding latents with VAE... 2026-07-12 09:12:48.798 | DEBUG | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:136 - [generate_music] Before VAE decode: allocated=5.98GB, max=7.29GB 2026-07-12 09:12:48.798 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:154 - [generate_music] Effective free VRAM before VAE decode: 87.72 GB 2026-07-12 09:12:48.798 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:172 - [generate_music] Using tiled VAE decode to reduce VRAM usage... 2026-07-12 09:12:48.798 | DEBUG | acestep.core.generation.handler.memory_utils:_get_auto_decode_chunk_size:108 - [_get_auto_decode_chunk_size] Effective free VRAM: 87.72 GB 2026-07-12 09:12:48.798 | DEBUG | acestep.core.generation.handler.memory_utils:_should_offload_wav_to_cpu:131 - [_should_offload_wav_to_cpu] Effective free VRAM: 87.72 GB 2026-07-12 09:12:48.798 | INFO | acestep.core.generation.handler.vae_decode:tiled_decode:56 - [tiled_decode] chunk_size=512, offload_wav_to_cpu=False, latents_shape=torch.Size([1, 64, 2170]) 2026-07-12 09:12:49.073 | DEBUG | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:193 - [generate_music] After VAE decode: allocated=6.15GB, max=7.44GB 2026-07-12 09:12:49.234 | INFO | acestep.core.generation.handler.generate_music_payload:_build_generate_music_success_payload:38 - [generate_music] VAE decode completed. Preparing audio tensors... 2026-07-12 09:12:49.237 | INFO | acestep.core.generation.handler.generate_music_payload:_build_generate_music_success_payload:50 - [generate_music] Done! Generated 1 audio tensors. [Request] Parsed ggml-sft/request0.json [Request] seed=42 lm_batch=1 synth_batch=1 [Request] caption: An upbeat and anthemic pop-rock track driven by bright, slig... [Request] lyrics: 490 bytes [Request] bpm=83 dur=88 key=G major ts=4 lang=fr [Request] lm: temp=0.85 cfg=2.0 top_p=0.90 top_k=0 [Request] dit: steps=50 guidance=1.0 shift=1.0 [Request] task_type: text2music [Request] solver: euler (stork_substeps=10) [Request] lm_mode: generate [Request] output_format: mp3 [Request] synth_model: acestep-v15-sft-BF16.gguf [Request] vae: vae-BF16.gguf [Request] audio_codes: (present) [Ace-Synth] Batch: 1 request(s) [Registry] Qwen3-Embedding-0.6B-BF16.gguf -> Text-Enc [Registry] Qwen3-Embedding-0.6B-Q8_0.gguf -> Text-Enc [Registry] acestep-5Hz-lm-0.6B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-0.6B-Q8_0.gguf -> LM [Registry] acestep-5Hz-lm-1.7B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-1.7B-Q8_0.gguf -> LM [Registry] acestep-5Hz-lm-4B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q5_K_M.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q6_K.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q8_0.gguf -> LM [Registry] acestep-v15-base-BF16.gguf -> DiT [Registry] acestep-v15-base-Q4_K_M.gguf -> DiT [Registry] acestep-v15-base-Q5_K_M.gguf -> DiT [Registry] acestep-v15-base-Q6_K.gguf -> DiT [Registry] acestep-v15-base-Q8_0.gguf -> DiT [Registry] acestep-v15-sft-BF16.gguf -> DiT [Registry] acestep-v15-sft-Q4_K_M.gguf -> DiT [Registry] acestep-v15-sft-Q5_K_M.gguf -> DiT [Registry] acestep-v15-sft-Q6_K.gguf -> DiT [Registry] acestep-v15-sft-Q8_0.gguf -> DiT [Registry] acestep-v15-sftturbo50-BF16.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q4_K_M.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q5_K_M.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q6_K.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-BF16.gguf -> DiT [Registry] acestep-v15-turbo-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-continuous-BF16.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-shift1-BF16.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-shift3-BF16.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-base-BF16.gguf -> DiT [Registry] acestep-v15-xl-base-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-base-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-base-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-base-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-sft-BF16.gguf -> DiT [Registry] acestep-v15-xl-sft-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-sft-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-sft-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-sft-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-BF16.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-turbo-BF16.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q8_0.gguf -> DiT [Registry] scragvae-BF16.gguf -> VAE [Registry] vae-BF16.gguf -> VAE [Store] Created (policy=STRICT) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-sft-BF16.gguf: 678 tensors, data at offset 56960 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-sft-BF16.gguf: 678 tensors, data at offset 56960 [Synth-Load] Ready: turbo=no, fa=no, batch_cfg=yes [Resolve-Params] max audio codes across batch: 434 (86.8s @ 5Hz) [Resolve-T] T=2170, S=1085 [Resolve-T] seed=42, steps=50, guidance=1.0, shift=1.0, duration=88.0s [BPE] Loaded from GGUF: 151643 vocab, 151387 merges ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): Device 0: NVIDIA RTX PRO 6000 Blackwell Workstation Edition, compute capability 12.0, VMM: yes, VRAM: 97247 MiB load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = NVIDIA RTX PRO 6000 Blackwell Workstation Edition (NVIDIA) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2 load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] TextEncoder backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/Qwen3-Embedding-0.6B-BF16.gguf: 310 tensors, data at offset 5337568 [Load] TextEncoder: 28L, H=1024, Nh=16/8 [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 310 tensors, 1136.5 MB into backend [Store] Load TextEnc: 224 ms [Debug] text_hidden: [70, 1024] first4: 3.704526 2.436253 0.222853 -13.131872 [Debug] lyric_embed: [167, 1024] first4: 0.029175 0.032227 -0.022339 -0.028809 [Store] Unload TextEnc (1136.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] CondEncoder backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-sft-BF16.gguf: 678 tensors, data at offset 56960 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 140 tensors, 1160.5 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L), text_proj, null_cond [Store] Load CondEnc: 825 ms [CondEnc] Lyric sliding mask: 167x167, window=128 [CondEnc] Timbre sliding mask: 1x1, window=128 [Encode] Packed: lyric=167 + timbre=1 + text=70 = 238 tokens [Encode-Text Batch0] 70+167 tokens -> enc_S=238, 99.8 ms [Debug] enc_hidden: [238, 2048] first4: 1.758276 -0.049599 -0.132827 0.058514 [Store] Unload CondEnc (1160.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] Detokenizer backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-sft-BF16.gguf: 678 tensors, data at offset 56960 [WeightCtx] Loaded 30 tensors, 200.3 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 128 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 899.1 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.124172 1.435321 0.310164 -0.624504 [Store] Unload FSQ-Detok (200.3 MB) [Init-Noise Batch0] Philox noise seed=42, [2170, 64] solver=euler [Debug] noise: [2170, 64] first4: 0.194336 2.156250 -0.171875 0.847656 [Debug] context: [2170, 128] first4: -0.124172 1.435321 0.310164 -0.624504 [Init-Noise] Starting: T=2170, S=1085, enc_S=238, steps=50, batch=1 (cover) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] DiT backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-sft-BF16.gguf: 678 tensors, data at offset 56960 [DiT] Self-attn: Q+K+V fused [DiT] Cross-attn: Q+K+V fused [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 478 tensors, 3007.9 MB into backend [Load] DiT: 24 layers, H=2048, Nh=16/8, D=128 [Store] Load DiT: 1577 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2129 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [12288] first4: 0.155061 -0.116337 -0.087159 0.082613 [Debug] temb: [2048] first4: -0.002789 -0.176915 0.004231 -0.001984 [Debug] temb_t: [2048] first4: -0.001270 0.003305 -0.013137 -0.002086 [Debug] temb_r: [2048] first4: -0.001519 -0.180220 0.017368 0.000102 [Debug] sinusoidal_t: [256] first4: 0.562379 0.789627 0.439928 -0.023645 [Debug] sinusoidal_r: [256] first4: 1.000000 1.000000 1.000000 1.000000 [Debug] temb_lin1_t: [2048] first4: -0.039439 0.029574 0.028407 -0.024894 [Debug] temb_lin1_r: [2048] first4: 0.002274 0.002999 -0.001040 -0.000388 [Debug] hidden_after_proj_in: [2048, 1085] first4: -1.090499 -0.926464 0.495247 0.440201 [Debug] proj_in_input: [192, 2170] first4: -0.124172 1.435321 0.310164 -0.624504 [Debug] enc_after_cond_emb: [2048, 238] first4: -0.188757 0.875783 0.328665 -0.577830 [Debug] layer0_sa_input: [2048, 1085] first4: -0.918423 -0.718803 -0.038139 0.295172 [Debug] layer0_q_after_rope: [128, 16] first4: -1.808892 -1.387187 -0.135358 0.377958 [Debug] layer0_k_after_rope: [128, 8] first4: -0.188757 0.875783 0.328665 -0.577830 [Debug] layer0_sa_output: [2048, 1085] first4: -1.649195 0.808645 -0.556233 0.543696 [Debug] layer0_attn_out: [2048, 1085] first4: -1.808892 -1.387187 -0.135358 0.377958 [Debug] layer0_after_self_attn: [2048, 1085] first4: -1.808892 -1.387187 -0.135358 0.377958 [Debug] layer0_after_cross_attn: [2048, 1085] first4: -1.971036 -1.049833 -0.413624 0.383357 [Debug] hidden_after_layer0: [2048, 1085] first4: -9.557844 1.194601 58.143230 -1.642145 [Debug] hidden_after_layer6: [2048, 1085] first4: -17.473732 4.451920 57.714855 -2.524643 [Debug] hidden_after_layer12: [2048, 1085] first4: -9.789162 4.848970 -20.656143 -2.014215 [Debug] hidden_after_layer18: [2048, 1085] first4: -3.175152 18.849306 -35.539726 -11.244928 [Debug] hidden_after_layer23: [2048, 1085] first4: 33.378967 64.624985 59.612682 -9.689672 [Debug] dit_step0_vt: [2170, 64] first4: -0.581620 2.525226 -0.201663 1.465749 [Debug] dit_step0_xt: [2170, 64] first4: 0.205968 2.105746 -0.167842 0.818341 [DiT] Step 1/50 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.648619 2.536328 -0.028497 1.299685 [Debug] dit_step1_xt: [2170, 64] first4: 0.218941 2.055019 -0.167272 0.792348 [DiT] Step 2/50 t=0.980 [Debug] dit_step2_vt: [2170, 64] first4: -0.646851 2.491205 0.005344 1.318794 [Debug] dit_step2_xt: [2170, 64] first4: 0.231878 2.005195 -0.167379 0.765972 [DiT] Step 3/50 t=0.960 [Debug] dit_step3_vt: [2170, 64] first4: -0.624331 2.433946 0.026509 1.326102 [Debug] dit_step3_xt: [2170, 64] first4: 0.244364 1.956516 -0.167909 0.739450 [DiT] Step 4/50 t=0.940 [Debug] dit_step4_vt: [2170, 64] first4: -0.568358 2.344923 0.006659 1.321841 [Debug] dit_step4_xt: [2170, 64] first4: 0.255732 1.909617 -0.168042 0.713013 [DiT] Step 5/50 t=0.920 [Debug] dit_step5_vt: [2170, 64] first4: -0.540510 2.290946 -0.021219 1.309145 [Debug] dit_step5_xt: [2170, 64] first4: 0.266542 1.863798 -0.167618 0.686830 [DiT] Step 6/50 t=0.900 [Debug] dit_step6_vt: [2170, 64] first4: -0.507919 2.227365 -0.053542 1.298645 [Debug] dit_step6_xt: [2170, 64] first4: 0.276700 1.819251 -0.166547 0.660857 [DiT] Step 7/50 t=0.880 [Debug] dit_step7_vt: [2170, 64] first4: -0.463547 2.160049 -0.074018 1.283235 [Debug] dit_step7_xt: [2170, 64] first4: 0.285971 1.776050 -0.165066 0.635192 [DiT] Step 8/50 t=0.860 [Debug] dit_step8_vt: [2170, 64] first4: -0.402033 2.064819 -0.087984 1.262099 [Debug] dit_step8_xt: [2170, 64] first4: 0.294012 1.734754 -0.163307 0.609950 [DiT] Step 9/50 t=0.840 [Debug] dit_step9_vt: [2170, 64] first4: -0.338877 1.972970 -0.093641 1.244855 [Debug] dit_step9_xt: [2170, 64] first4: 0.300789 1.695294 -0.161434 0.585053 [DiT] Step 10/50 t=0.820 [Debug] dit_step10_vt: [2170, 64] first4: -0.271688 1.889462 -0.077603 1.235510 [Debug] dit_step10_xt: [2170, 64] first4: 0.306223 1.657505 -0.159882 0.560343 [DiT] Step 11/50 t=0.800 [Debug] dit_step11_vt: [2170, 64] first4: -0.232332 1.813437 -0.075055 1.234986 [Debug] dit_step11_xt: [2170, 64] first4: 0.310870 1.621236 -0.158381 0.535643 [DiT] Step 12/50 t=0.780 [Debug] dit_step12_vt: [2170, 64] first4: -0.206181 1.742622 -0.087321 1.219010 [Debug] dit_step12_xt: [2170, 64] first4: 0.314993 1.586384 -0.156634 0.511263 [DiT] Step 13/50 t=0.760 [Debug] dit_step13_vt: [2170, 64] first4: -0.193771 1.671303 -0.106323 1.200053 [Debug] dit_step13_xt: [2170, 64] first4: 0.318869 1.552958 -0.154508 0.487262 [DiT] Step 14/50 t=0.740 [Debug] dit_step14_vt: [2170, 64] first4: -0.187309 1.591692 -0.131943 1.185596 [Debug] dit_step14_xt: [2170, 64] first4: 0.322615 1.521124 -0.151869 0.463550 [DiT] Step 15/50 t=0.720 [Debug] dit_step15_vt: [2170, 64] first4: -0.185428 1.508886 -0.170669 1.165323 [Debug] dit_step15_xt: [2170, 64] first4: 0.326323 1.490946 -0.148456 0.440244 [DiT] Step 16/50 t=0.700 [Debug] dit_step16_vt: [2170, 64] first4: -0.193209 1.436094 -0.196551 1.146308 [Debug] dit_step16_xt: [2170, 64] first4: 0.330188 1.462224 -0.144525 0.417318 [DiT] Step 17/50 t=0.680 [Debug] dit_step17_vt: [2170, 64] first4: -0.205434 1.352405 -0.222775 1.127202 [Debug] dit_step17_xt: [2170, 64] first4: 0.334296 1.435176 -0.140069 0.394774 [DiT] Step 18/50 t=0.660 [Debug] dit_step18_vt: [2170, 64] first4: -0.221665 1.275156 -0.251119 1.109041 [Debug] dit_step18_xt: [2170, 64] first4: 0.338730 1.409673 -0.135047 0.372593 [DiT] Step 19/50 t=0.640 [Debug] dit_step19_vt: [2170, 64] first4: -0.236432 1.199435 -0.278728 1.086453 [Debug] dit_step19_xt: [2170, 64] first4: 0.343458 1.385684 -0.129472 0.350864 [DiT] Step 20/50 t=0.620 [Debug] dit_step20_vt: [2170, 64] first4: -0.254338 1.104942 -0.289876 1.063241 [Debug] dit_step20_xt: [2170, 64] first4: 0.348545 1.363586 -0.123675 0.329599 [DiT] Step 21/50 t=0.600 [Debug] dit_step21_vt: [2170, 64] first4: -0.278154 1.012809 -0.295685 1.038993 [Debug] dit_step21_xt: [2170, 64] first4: 0.354108 1.343329 -0.117761 0.308819 [DiT] Step 22/50 t=0.580 [Debug] dit_step22_vt: [2170, 64] first4: -0.299081 0.917677 -0.304726 1.013200 [Debug] dit_step22_xt: [2170, 64] first4: 0.360090 1.324976 -0.111666 0.288555 [DiT] Step 23/50 t=0.560 [Debug] dit_step23_vt: [2170, 64] first4: -0.321065 0.817508 -0.311347 0.980928 [Debug] dit_step23_xt: [2170, 64] first4: 0.366511 1.308626 -0.105440 0.268936 [DiT] Step 24/50 t=0.540 [Debug] dit_step24_vt: [2170, 64] first4: -0.346113 0.712485 -0.311124 0.964189 [Debug] dit_step24_xt: [2170, 64] first4: 0.373433 1.294376 -0.099217 0.249653 [DiT] Step 25/50 t=0.520 [Debug] dit_step25_vt: [2170, 64] first4: -0.369914 0.600366 -0.308905 0.944250 [Debug] dit_step25_xt: [2170, 64] first4: 0.380831 1.282369 -0.093039 0.230768 [DiT] Step 26/50 t=0.500 [Debug] dit_step26_vt: [2170, 64] first4: -0.393770 0.480124 -0.304213 0.917152 [Debug] dit_step26_xt: [2170, 64] first4: 0.388707 1.272766 -0.086955 0.212425 [DiT] Step 27/50 t=0.480 [Debug] dit_step27_vt: [2170, 64] first4: -0.418193 0.360931 -0.296828 0.900663 [Debug] dit_step27_xt: [2170, 64] first4: 0.397071 1.265548 -0.081018 0.194411 [DiT] Step 28/50 t=0.460 [Debug] dit_step28_vt: [2170, 64] first4: -0.443789 0.243298 -0.287361 0.877352 [Debug] dit_step28_xt: [2170, 64] first4: 0.405946 1.260682 -0.075271 0.176864 [DiT] Step 29/50 t=0.440 [Debug] dit_step29_vt: [2170, 64] first4: -0.466368 0.128767 -0.284699 0.857364 [Debug] dit_step29_xt: [2170, 64] first4: 0.415274 1.258106 -0.069577 0.159717 [DiT] Step 30/50 t=0.420 [Debug] dit_step30_vt: [2170, 64] first4: -0.485948 0.012503 -0.274237 0.846572 [Debug] dit_step30_xt: [2170, 64] first4: 0.424993 1.257856 -0.064092 0.142786 [DiT] Step 31/50 t=0.400 [Debug] dit_step31_vt: [2170, 64] first4: -0.499227 -0.105612 -0.262862 0.819309 [Debug] dit_step31_xt: [2170, 64] first4: 0.434977 1.259968 -0.058835 0.126399 [DiT] Step 32/50 t=0.380 [Debug] dit_step32_vt: [2170, 64] first4: -0.514979 -0.222537 -0.237922 0.794308 [Debug] dit_step32_xt: [2170, 64] first4: 0.445277 1.264419 -0.054076 0.110513 [DiT] Step 33/50 t=0.360 [Debug] dit_step33_vt: [2170, 64] first4: -0.523884 -0.336637 -0.229521 0.776209 [Debug] dit_step33_xt: [2170, 64] first4: 0.455755 1.271152 -0.049486 0.094989 [DiT] Step 34/50 t=0.340 [Debug] dit_step34_vt: [2170, 64] first4: -0.543620 -0.440082 -0.204816 0.749319 [Debug] dit_step34_xt: [2170, 64] first4: 0.466627 1.279953 -0.045390 0.080003 [DiT] Step 35/50 t=0.320 [Debug] dit_step35_vt: [2170, 64] first4: -0.544526 -0.532059 -0.182779 0.730998 [Debug] dit_step35_xt: [2170, 64] first4: 0.477518 1.290595 -0.041734 0.065383 [DiT] Step 36/50 t=0.300 [Debug] dit_step36_vt: [2170, 64] first4: -0.549069 -0.626440 -0.160271 0.704139 [Debug] dit_step36_xt: [2170, 64] first4: 0.488499 1.303123 -0.038529 0.051300 [DiT] Step 37/50 t=0.280 [Debug] dit_step37_vt: [2170, 64] first4: -0.558365 -0.717204 -0.135892 0.664571 [Debug] dit_step37_xt: [2170, 64] first4: 0.499666 1.317467 -0.035811 0.038009 [DiT] Step 38/50 t=0.260 [Debug] dit_step38_vt: [2170, 64] first4: -0.552536 -0.802641 -0.109979 0.631734 [Debug] dit_step38_xt: [2170, 64] first4: 0.510717 1.333520 -0.033611 0.025374 [DiT] Step 39/50 t=0.240 [Debug] dit_step39_vt: [2170, 64] first4: -0.547804 -0.885644 -0.067001 0.593909 [Debug] dit_step39_xt: [2170, 64] first4: 0.521673 1.351233 -0.032271 0.013496 [DiT] Step 40/50 t=0.220 [Debug] dit_step40_vt: [2170, 64] first4: -0.539952 -0.951504 -0.039988 0.552331 [Debug] dit_step40_xt: [2170, 64] first4: 0.532472 1.370263 -0.031472 0.002449 [DiT] Step 41/50 t=0.200 [Debug] dit_step41_vt: [2170, 64] first4: -0.523637 -1.016746 0.004996 0.503382 [Debug] dit_step41_xt: [2170, 64] first4: 0.542945 1.390598 -0.031571 -0.007619 [DiT] Step 42/50 t=0.180 [Debug] dit_step42_vt: [2170, 64] first4: -0.510831 -1.079088 0.040937 0.454476 [Debug] dit_step42_xt: [2170, 64] first4: 0.553161 1.412180 -0.032390 -0.016708 [DiT] Step 43/50 t=0.160 [Debug] dit_step43_vt: [2170, 64] first4: -0.500082 -1.134202 0.073540 0.397771 [Debug] dit_step43_xt: [2170, 64] first4: 0.563163 1.434864 -0.033861 -0.024664 [DiT] Step 44/50 t=0.140 [Debug] dit_step44_vt: [2170, 64] first4: -0.477484 -1.183322 0.115335 0.348574 [Debug] dit_step44_xt: [2170, 64] first4: 0.572713 1.458530 -0.036168 -0.031635 [DiT] Step 45/50 t=0.120 [Debug] dit_step45_vt: [2170, 64] first4: -0.459519 -1.223033 0.147924 0.281787 [Debug] dit_step45_xt: [2170, 64] first4: 0.581903 1.482991 -0.039126 -0.037271 [DiT] Step 46/50 t=0.100 [Debug] dit_step46_vt: [2170, 64] first4: -0.443882 -1.257669 0.179232 0.235137 [Debug] dit_step46_xt: [2170, 64] first4: 0.590781 1.508144 -0.042711 -0.041974 [DiT] Step 47/50 t=0.080 [Debug] dit_step47_vt: [2170, 64] first4: -0.412024 -1.290818 0.196469 0.193292 [Debug] dit_step47_xt: [2170, 64] first4: 0.599021 1.533961 -0.046640 -0.045839 [DiT] Step 48/50 t=0.060 [Debug] dit_step48_vt: [2170, 64] first4: -0.369562 -1.311687 0.209102 0.156523 [Debug] dit_step48_xt: [2170, 64] first4: 0.606413 1.560194 -0.050822 -0.048970 [DiT] Step 49/50 t=0.040 [Debug] dit_step49_vt: [2170, 64] first4: -0.404070 -1.344562 0.192819 0.149416 [Debug] dit_x0: [2170, 64] first4: 0.614494 1.587086 -0.054679 -0.051958 [DiT] Step 50/50 t=0.020 [DiT-Generate] Total: 118354.3 ms (118354.3 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.614494 1.587086 -0.054679 -0.051958 [Store] Unload DiT (3007.9 MB) [GGUF] /mnt/workspace/git/acestep.cpp/models/vae-BF16.gguf: 365 tensors, data at offset 30048 load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] VAE backend: CPU (CPU threads: 16) [VAE] Backend: CPU, Weight buffer: 161.1 MB [VAE] Loaded: 5 blocks, upsample=1920x, F32 activations [Store] Load VAE-Dec: 716 ms [VAE] Tiled decode: 3 tiles (chunk=1024, overlap=64, stride=896) [VAE] Graph: 479 nodes, T_latent=960 [VAE] Upsample factor: 1920.00 (expected ~1920) [VAE] Graph: 479 nodes, T_latent=1024 [VAE] Graph: 479 nodes, T_latent=442 [VAE] Tiled decode done: 3 tiles -> T_audio=4166400 (86.80s @ 48kHz) [VAE-Decode Batch0] Decode: 33967.1 ms [Debug] vae_audio: [2, 4166400] first4: -0.001522 -0.000981 -0.001248 -0.000839 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 423 ms (205.07x realtime), 32 threads [MP3] Wrote ggml-sft/request00.mp3 [Ace-Synth] All done 2026-07-12 09:15:27.597 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:174 - [initialize_service] Attempting to load model with attention implementation: sdpa 2026-07-12 09:15:28.706 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 09:15:28.706 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 09:15:28.706 | INFO | acestep.core.generation.handler.generate_music_request:_prepare_reference_and_source_audio:179 - [generate_music] cover task: no src_audio but audio codes provided, proceeding with codes 2026-07-12 09:15:28.709 | INFO | acestep.core.generation.handler.generate_music:_vram_preflight_check:156 - [generate_music] VRAM pre-flight: 81.69 GB free, ~0.94 GB needed (batch=1, duration=88s, mode=turbo). 2026-07-12 09:15:28.714 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 09:15:28.719 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_precomputed_lm_hints:31 - [generate_music] Decoding audio codes for LM hints for item 0... 2026-07-12 09:15:28.720 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 09:15:28.720 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 09:15:28.720 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 09:15:28.720 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:122 - text_prompt: # Instruction Generate audio semantic tokens based on the given conditions: # Caption An upbeat and anthemic pop-rock track driven by bright, slightly overdriven # Metas - bpm: 83 - timesignature: 4 - keyscale: G major - duration: 88 seconds <|endoftext|> 2026-07-12 09:15:28.720 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 09:15:28.720 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:124 - lyrics_text: # Languages fr # Lyric # Lyric [Intro - Guitar Riff] [Verse 1] Dans le monde des tutos virtuels G ta toise en nouvelle passion Avec Ggendoline et PumbΓ© Γ  midi La communautΓ©, c'est l'unitΓ© Quel joie, une clΓ© [Chorus] Dans le monde des tutos virtuels GΓ’ndoline et PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner [Guitar Solo] [Verse 2] Dans le monde des tutos virtuels GΓ’ndoline, PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner<|endoftext|> 2026-07-12 09:15:28.720 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 09:15:28.724 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 09:15:28.732 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 09:15:28.732 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 09:15:28.739 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)... [Request] Loaded request0.json [Turbo] steps=8, shift=3.0 | acestep-v15-turbo-BF16.gguf [GGML] Running acestep-v15-turbo-BF16.gguf... [GGML] Done, 47 dump files [Python] Initializing acestep-v15-turbo... [Python] Generating (acestep-v15-turbo, 8 steps)... Using precomputed LM hints Using precomputed LM hints [Python] Wrote python-turbo/output.wav: 4166400 samples (86.80s @ 48kHz stereo) [Python] Done, 40 dump files [Turbo] Cosine similarities GGML vs Python stage GGML vs Python text_hidden 0.999810 lyric_embed 1.000000 enc_hidden 0.999836 detok_output 0.999996 context 0.999997 noise 1.000000 temb_t 0.999999 hidden_after_proj_in 0.999988 enc_after_cond_emb 0.999829 layer0_sa_output 0.999960 hidden_after_layer0 0.999982 hidden_after_layer6 0.999923 hidden_after_layer12 0.999334 hidden_after_layer18 0.996714 hidden_after_layer23 0.993821 dit_step0_vt 0.975849 dit_step0_xt 0.999947 dit_step1_vt 0.979487 dit_step1_xt 0.999833 dit_step2_vt 0.981791 dit_step2_xt 0.999554 dit_step3_vt 0.982387 dit_step3_xt 0.998920 dit_step4_vt 0.980796 dit_step4_xt 0.997488 dit_step5_vt 0.978042 dit_step5_xt 0.994277 dit_step6_vt 0.974833 dit_step6_xt 0.988160 dit_step7_vt 0.969098 dit_x0 0.979123 vae_audio 0.901817 vae_audio (STFT cosine) 0.975801 [Turbo] Error growth GGML vs Python stage cos max_err mean_err mean_A std_A mean_B std_B dit_step0_xt 0.999947 0.136835 0.006598 -0.002311 0.972945 -0.002342 0.972003 dit_step1_xt 0.999833 0.266113 0.011271 -0.005310 0.942680 -0.005313 0.941730 dit_step2_xt 0.999554 0.451848 0.017463 -0.009351 0.909200 -0.009311 0.908527 dit_step3_xt 0.998920 0.642987 0.025943 -0.014719 0.873841 -0.014577 0.873624 dit_step4_xt 0.997488 0.780718 0.037845 -0.021766 0.842029 -0.021660 0.841995 dit_step5_xt 0.994277 1.239408 0.055620 -0.031842 0.825348 -0.032109 0.824593 dit_step6_xt 0.988160 2.070782 0.082599 -0.046121 0.856209 -0.046482 0.855546 [SFT] steps=50, shift=1.0 | acestep-v15-sft-BF16.gguf [GGML] Running acestep-v15-sft-BF16.gguf... [GGML] Done, 131 dump files [Python] Initializing acestep-v15-sft... [Python] Generating (acestep-v15-sft, 50 steps)... Using precomputed LM hints Using precomputed LM hints 0%| | 0/50 [00:00 Text-Enc [Registry] Qwen3-Embedding-0.6B-Q8_0.gguf -> Text-Enc [Registry] acestep-5Hz-lm-0.6B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-0.6B-Q8_0.gguf -> LM [Registry] acestep-5Hz-lm-1.7B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-1.7B-Q8_0.gguf -> LM [Registry] acestep-5Hz-lm-4B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q5_K_M.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q6_K.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q8_0.gguf -> LM [Registry] acestep-v15-base-BF16.gguf -> DiT [Registry] acestep-v15-base-Q4_K_M.gguf -> DiT [Registry] acestep-v15-base-Q5_K_M.gguf -> DiT [Registry] acestep-v15-base-Q6_K.gguf -> DiT [Registry] acestep-v15-base-Q8_0.gguf -> DiT [Registry] acestep-v15-sft-BF16.gguf -> DiT [Registry] acestep-v15-sft-Q4_K_M.gguf -> DiT [Registry] acestep-v15-sft-Q5_K_M.gguf -> DiT [Registry] acestep-v15-sft-Q6_K.gguf -> DiT [Registry] acestep-v15-sft-Q8_0.gguf -> DiT [Registry] acestep-v15-sftturbo50-BF16.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q4_K_M.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q5_K_M.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q6_K.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-BF16.gguf -> DiT [Registry] acestep-v15-turbo-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-continuous-BF16.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-shift1-BF16.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-shift3-BF16.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-base-BF16.gguf -> DiT [Registry] acestep-v15-xl-base-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-base-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-base-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-base-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-sft-BF16.gguf -> DiT [Registry] acestep-v15-xl-sft-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-sft-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-sft-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-sft-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-BF16.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-turbo-BF16.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q8_0.gguf -> DiT [Registry] scragvae-BF16.gguf -> VAE [Registry] vae-BF16.gguf -> VAE [Store] Created (policy=STRICT) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-turbo-BF16.gguf: 830 tensors, data at offset 69344 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-turbo-BF16.gguf: 830 tensors, data at offset 69344 [Synth-Load] Ready: turbo=yes, fa=no, batch_cfg=yes [Resolve-Params] max audio codes across batch: 434 (86.8s @ 5Hz) [Resolve-T] T=2170, S=1085 [Resolve-T] seed=42, steps=8, guidance=1.0, shift=3.0, duration=88.0s [BPE] Loaded from GGUF: 151643 vocab, 151387 merges ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): Device 0: NVIDIA RTX PRO 6000 Blackwell Workstation Edition, compute capability 12.0, VMM: yes, VRAM: 97247 MiB load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = NVIDIA RTX PRO 6000 Blackwell Workstation Edition (NVIDIA) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2 load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] TextEncoder backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/Qwen3-Embedding-0.6B-BF16.gguf: 310 tensors, data at offset 5337568 [Load] TextEncoder: 28L, H=1024, Nh=16/8 [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 310 tensors, 1136.5 MB into backend [Store] Load TextEnc: 235 ms [Debug] text_hidden: [70, 1024] first4: 3.704526 2.436253 0.222853 -13.131872 [Debug] lyric_embed: [167, 1024] first4: 0.029175 0.032227 -0.022339 -0.028809 [Store] Unload TextEnc (1136.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] CondEncoder backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-turbo-BF16.gguf: 830 tensors, data at offset 69344 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 141 tensors, 1160.5 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L, CLS), text_proj, null_cond [Store] Load CondEnc: 790 ms [CondEnc] Lyric sliding mask: 167x167, window=128 [CondEnc] Timbre sliding mask: 2x2, window=128 (CLS) [Encode] Packed: lyric=167 + timbre=1 + text=70 = 238 tokens [Encode-Text Batch0] 70+167 tokens -> enc_S=238, 100.1 ms [Debug] enc_hidden: [238, 2048] first4: 0.686898 -0.019098 -0.051494 0.022655 [Store] Unload CondEnc (1160.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] Detokenizer backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-turbo-BF16.gguf: 830 tensors, data at offset 69344 [WeightCtx] Loaded 30 tensors, 200.3 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 109 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 905.4 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.124172 1.435321 0.310164 -0.624504 [Store] Unload FSQ-Detok (200.3 MB) [Init-Noise Batch0] Philox noise seed=42, [2170, 64] solver=euler [Debug] noise: [2170, 64] first4: 0.194336 2.156250 -0.171875 0.847656 [Debug] context: [2170, 128] first4: -0.124172 1.435321 0.310164 -0.624504 [Init-Noise] Starting: T=2170, S=1085, enc_S=238, steps=8, batch=1 (cover) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] DiT backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-turbo-BF16.gguf: 830 tensors, data at offset 69344 [DiT] Self-attn: Q+K+V fused [DiT] Cross-attn: Q+K+V fused [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 630 tensors, 7955.6 MB into backend [Load] DiT: 32 layers, H=2560, Nh=32/8, D=128 [Store] Load DiT: 5363 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2825 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [15360] first4: 0.016426 0.108683 0.065360 -0.074070 [Debug] temb: [2560] first4: 0.026340 -0.023021 -0.016529 0.047201 [Debug] temb_t: [2560] first4: 0.014587 -0.022342 -0.020864 0.048816 [Debug] temb_r: [2560] first4: 0.011753 -0.000679 0.004335 -0.001615 [Debug] sinusoidal_t: [256] first4: 0.562379 0.789627 0.439928 -0.023645 [Debug] sinusoidal_r: [256] first4: 1.000000 1.000000 1.000000 1.000000 [Debug] temb_lin1_t: [2560] first4: 0.063947 -0.019714 0.138310 -0.113208 [Debug] temb_lin1_r: [2560] first4: -0.009879 0.015926 -0.017671 0.012016 [Debug] hidden_after_proj_in: [2560, 1085] first4: 0.337150 -0.577257 0.230419 -0.190830 [Debug] proj_in_input: [192, 2170] first4: -0.124172 1.435321 0.310164 -0.624504 [Debug] enc_after_cond_emb: [2560, 238] first4: 0.030978 0.651376 0.102890 0.871310 [Debug] layer0_sa_input: [2560, 1085] first4: 0.039979 -0.045431 0.093871 -0.134719 [Debug] layer0_q_after_rope: [128, 32] first4: -0.240838 -2.074609 0.340630 0.212767 [Debug] layer0_k_after_rope: [128, 8] first4: 0.020321 2.181354 0.699668 0.516729 [Debug] layer0_sa_output: [2560, 1085] first4: 1.632464 4.282640 -0.558102 5.413632 [Debug] layer0_attn_out: [4096, 1085] first4: 0.466511 -2.236335 -0.177157 -2.789362 [Debug] layer0_after_self_attn: [2560, 1085] first4: 0.466511 -2.236335 -0.177157 -2.789362 [Debug] layer0_after_cross_attn: [2560, 1085] first4: 0.335877 -1.990901 -0.007252 -3.742178 [Debug] hidden_after_layer0: [2560, 1085] first4: 1.722611 -2.430920 241.825974 -3.714182 [Debug] hidden_after_layer6: [2560, 1085] first4: -6.174104 -2.155552 321.130463 -12.388517 [Debug] hidden_after_layer12: [2560, 1085] first4: -10.868447 29.452194 264.720306 28.747551 [Debug] hidden_after_layer18: [2560, 1085] first4: 42.068722 14.974079 278.738159 5.103224 [Debug] hidden_after_layer31: [2560, 1085] first4: -79.931030 -237.501785 -167.839706 174.702591 [Debug] dit_step0_vt: [2170, 64] first4: -1.215084 1.553296 0.396014 1.184635 [Debug] dit_step0_xt: [2170, 64] first4: 0.249567 2.085646 -0.189876 0.793809 [DiT] Step 1/8 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.664746 2.489604 0.842081 1.059206 [Debug] dit_step1_xt: [2170, 64] first4: 0.285826 1.949849 -0.235807 0.736034 [DiT] Step 2/8 t=0.955 [Debug] dit_step2_vt: [2170, 64] first4: -1.137094 2.213027 0.933505 1.018314 [Debug] dit_step2_xt: [2170, 64] first4: 0.361632 1.802314 -0.298041 0.668147 [DiT] Step 3/8 t=0.900 [Debug] dit_step3_vt: [2170, 64] first4: -1.359937 2.364017 1.099361 0.496145 [Debug] dit_step3_xt: [2170, 64] first4: 0.474960 1.605313 -0.389654 0.626801 [DiT] Step 4/8 t=0.833 [Debug] dit_step4_vt: [2170, 64] first4: -0.960422 2.206104 1.129881 0.204636 [Debug] dit_step4_xt: [2170, 64] first4: 0.577863 1.368944 -0.510713 0.604876 [DiT] Step 5/8 t=0.750 [Debug] dit_step5_vt: [2170, 64] first4: -1.175987 2.258690 0.890145 0.801434 [Debug] dit_step5_xt: [2170, 64] first4: 0.745861 1.046274 -0.637877 0.490385 [DiT] Step 6/8 t=0.643 [Debug] dit_step6_vt: [2170, 64] first4: -0.970684 2.009483 0.629019 0.824656 [Debug] dit_step6_xt: [2170, 64] first4: 0.939998 0.644378 -0.763680 0.325454 [DiT] Step 7/8 t=0.500 [Debug] dit_step7_vt: [2170, 64] first4: -1.036474 1.570236 0.639234 0.604436 [Debug] dit_x0: [2170, 64] first4: 1.250940 0.173307 -0.955451 0.144123 [DiT] Step 8/8 t=0.300 [DiT-Generate] Total: 51745.7 ms (51745.7 ms/sample) [Debug] dit_output: [2170, 64] first4: 1.250940 0.173307 -0.955451 0.144123 [Store] Unload DiT (7955.6 MB) [GGUF] /mnt/workspace/git/acestep.cpp/models/vae-BF16.gguf: 365 tensors, data at offset 30048 load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] VAE backend: CPU (CPU threads: 16) [VAE] Backend: CPU, Weight buffer: 161.1 MB [VAE] Loaded: 5 blocks, upsample=1920x, F32 activations [Store] Load VAE-Dec: 762 ms [VAE] Tiled decode: 3 tiles (chunk=1024, overlap=64, stride=896) [VAE] Graph: 479 nodes, T_latent=960 [VAE] Upsample factor: 1920.00 (expected ~1920) [VAE] Graph: 479 nodes, T_latent=1024 [VAE] Graph: 479 nodes, T_latent=442 [VAE] Tiled decode done: 3 tiles -> T_audio=4166400 (86.80s @ 48kHz) [VAE-Decode Batch0] Decode: 32544.8 ms [Debug] vae_audio: [2, 4166400] first4: 0.001682 0.004385 0.004578 0.003903 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 533 ms (162.70x realtime), 32 threads [MP3] Wrote ggml-xl-turbo/request00.mp3 [Ace-Synth] All done 2026-07-12 09:17:05.420 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:174 - [initialize_service] Attempting to load model with attention implementation: sdpa [Python] Wrote python-sft/output.wav: 4166400 samples (86.80s @ 48kHz stereo) [Python] Done, 166 dump files [SFT] Cosine similarities GGML vs Python stage GGML vs Python text_hidden 0.999810 lyric_embed 1.000000 enc_hidden 0.999836 detok_output 0.999996 context 0.999997 noise 1.000000 temb_t 0.999998 hidden_after_proj_in 0.999988 enc_after_cond_emb 0.999829 layer0_sa_output 0.999957 hidden_after_layer0 0.999983 hidden_after_layer6 0.999852 hidden_after_layer12 0.999464 hidden_after_layer18 0.998728 hidden_after_layer23 0.998993 dit_step0_vt 0.998957 dit_step0_xt 1.000000 dit_step5_vt 0.999521 dit_step5_xt 0.999981 dit_step10_vt 0.999207 dit_step10_xt 0.999939 dit_step15_vt 0.998363 dit_step15_xt 0.999859 dit_step20_vt 0.996596 dit_step20_xt 0.999648 dit_step25_vt 0.993446 dit_step25_xt 0.999211 dit_step30_vt 0.989322 dit_step30_xt 0.998389 dit_step35_vt 0.984896 dit_step35_xt 0.997223 dit_step40_vt 0.982121 dit_step40_xt 0.995953 dit_step45_vt 0.985437 dit_step45_xt 0.995002 dit_step49_vt 0.990493 dit_x0 0.994667 vae_audio 0.971599 vae_audio (STFT cosine) 0.988881 [SFT] Error growth GGML vs Python stage cos max_err mean_err mean_A std_A mean_B std_B dit_step0_xt 1.000000 0.019908 0.001449 -0.001655 0.978462 -0.001619 0.978872 dit_step5_xt 0.999981 0.078142 0.004202 -0.008401 0.884789 -0.008480 0.883811 dit_step10_xt 0.999939 0.116878 0.006627 -0.015154 0.800968 -0.015075 0.802324 dit_step15_xt 0.999859 0.163477 0.009242 -0.021882 0.730558 -0.021933 0.731304 dit_step20_xt 0.999648 0.223037 0.013525 -0.028646 0.677784 -0.028882 0.679066 dit_step25_xt 0.999211 0.329347 0.019220 -0.035480 0.647071 -0.035643 0.650780 dit_step30_xt 0.998389 0.564865 0.026851 -0.042359 0.641694 -0.042577 0.647107 dit_step35_xt 0.997223 0.825883 0.036005 -0.049247 0.662376 -0.049471 0.669256 dit_step40_xt 0.995953 1.086389 0.046272 -0.056165 0.706782 -0.056532 0.715783 dit_step45_xt 0.995002 1.317524 0.055946 -0.063189 0.770632 -0.063533 0.780575 [Xl-turbo] steps=8, shift=3.0 | acestep-v15-xl-turbo-BF16.gguf [GGML] Running acestep-v15-xl-turbo-BF16.gguf... [GGML] Done, 47 dump files [Python] Initializing acestep-v15-xl-turbo... Loading checkpoint shards: 0%| | 0/4 [00:00 1.0 (turbo does not use CFG). 2026-07-12 09:17:07.875 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 09:17:07.875 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 09:17:07.876 | INFO | acestep.core.generation.handler.generate_music_request:_prepare_reference_and_source_audio:179 - [generate_music] cover task: no src_audio but audio codes provided, proceeding with codes 2026-07-12 09:17:07.878 | INFO | acestep.core.generation.handler.generate_music:_vram_preflight_check:156 - [generate_music] VRAM pre-flight: 76.75 GB free, ~1.23 GB needed (batch=1, duration=88s, mode=xl_turbo). 2026-07-12 09:17:07.884 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 09:17:07.889 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_precomputed_lm_hints:31 - [generate_music] Decoding audio codes for LM hints for item 0... 2026-07-12 09:17:07.891 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 09:17:07.891 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 09:17:07.891 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 09:17:07.891 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:122 - text_prompt: # Instruction Generate audio semantic tokens based on the given conditions: # Caption An upbeat and anthemic pop-rock track driven by bright, slightly overdriven # Metas - bpm: 83 - timesignature: 4 - keyscale: G major - duration: 88 seconds <|endoftext|> 2026-07-12 09:17:07.891 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 09:17:07.892 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:124 - lyrics_text: # Languages fr # Lyric # Lyric [Intro - Guitar Riff] [Verse 1] Dans le monde des tutos virtuels G ta toise en nouvelle passion Avec Ggendoline et PumbΓ© Γ  midi La communautΓ©, c'est l'unitΓ© Quel joie, une clΓ© [Chorus] Dans le monde des tutos virtuels GΓ’ndoline et PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner [Guitar Solo] [Verse 2] Dans le monde des tutos virtuels GΓ’ndoline, PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner<|endoftext|> 2026-07-12 09:17:07.892 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 09:17:07.895 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 09:17:07.903 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 09:17:07.903 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 09:17:07.909 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)... 2026-07-12 09:17:07.916 | INFO | acestep.models.common.dcw_correction:__init__:98 - [DCW] Active β€” mode=double, scaler=0.0500, high_scaler=0.0200, wavelet='haar' 2026-07-12 09:17:08.460 | INFO | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:42 - [generate_music] Model generation completed. Decoding latents... 2026-07-12 09:17:08.470 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:64 - [generate_music] pred_latents: torch.Size([1, 2170, 64]), dtype=torch.bfloat16 2026-07-12 09:17:08.470 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:65 - [generate_music] time_costs: {'encoder_time_cost': 0.006369829177856445, 'diffusion_time_cost': 0.5440847873687744, 'diffusion_per_step_time_cost': 0.0680105984210968, 'total_time_cost': 0.5504546165466309, 'offload_time_cost': 0.0} 2026-07-12 09:17:08.484 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:127 - [generate_music] Decoding latents with VAE... 2026-07-12 09:17:08.485 | DEBUG | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:136 - [generate_music] Before VAE decode: allocated=17.03GB, max=18.34GB 2026-07-12 09:17:08.485 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:154 - [generate_music] Effective free VRAM before VAE decode: 76.66 GB 2026-07-12 09:17:08.485 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:172 - [generate_music] Using tiled VAE decode to reduce VRAM usage... 2026-07-12 09:17:08.485 | DEBUG | acestep.core.generation.handler.memory_utils:_get_auto_decode_chunk_size:108 - [_get_auto_decode_chunk_size] Effective free VRAM: 76.66 GB 2026-07-12 09:17:08.485 | DEBUG | acestep.core.generation.handler.memory_utils:_should_offload_wav_to_cpu:131 - [_should_offload_wav_to_cpu] Effective free VRAM: 76.66 GB 2026-07-12 09:17:08.485 | INFO | acestep.core.generation.handler.vae_decode:tiled_decode:56 - [tiled_decode] chunk_size=512, offload_wav_to_cpu=False, latents_shape=torch.Size([1, 64, 2170]) 2026-07-12 09:17:08.756 | DEBUG | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:193 - [generate_music] After VAE decode: allocated=17.21GB, max=18.50GB 2026-07-12 09:17:08.967 | INFO | acestep.core.generation.handler.generate_music_payload:_build_generate_music_success_payload:38 - [generate_music] VAE decode completed. Preparing audio tensors... 2026-07-12 09:17:08.971 | INFO | acestep.core.generation.handler.generate_music_payload:_build_generate_music_success_payload:50 - [generate_music] Done! Generated 1 audio tensors. [Request] Parsed ggml-xl-sft/request0.json [Request] seed=42 lm_batch=1 synth_batch=1 [Request] caption: An upbeat and anthemic pop-rock track driven by bright, slig... [Request] lyrics: 490 bytes [Request] bpm=83 dur=88 key=G major ts=4 lang=fr [Request] lm: temp=0.85 cfg=2.0 top_p=0.90 top_k=0 [Request] dit: steps=50 guidance=1.0 shift=1.0 [Request] task_type: text2music [Request] solver: euler (stork_substeps=10) [Request] lm_mode: generate [Request] output_format: mp3 [Request] synth_model: acestep-v15-xl-sft-BF16.gguf [Request] vae: vae-BF16.gguf [Request] audio_codes: (present) [Ace-Synth] Batch: 1 request(s) [Registry] Qwen3-Embedding-0.6B-BF16.gguf -> Text-Enc [Registry] Qwen3-Embedding-0.6B-Q8_0.gguf -> Text-Enc [Registry] acestep-5Hz-lm-0.6B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-0.6B-Q8_0.gguf -> LM [Registry] acestep-5Hz-lm-1.7B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-1.7B-Q8_0.gguf -> LM [Registry] acestep-5Hz-lm-4B-BF16.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q5_K_M.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q6_K.gguf -> LM [Registry] acestep-5Hz-lm-4B-Q8_0.gguf -> LM [Registry] acestep-v15-base-BF16.gguf -> DiT [Registry] acestep-v15-base-Q4_K_M.gguf -> DiT [Registry] acestep-v15-base-Q5_K_M.gguf -> DiT [Registry] acestep-v15-base-Q6_K.gguf -> DiT [Registry] acestep-v15-base-Q8_0.gguf -> DiT [Registry] acestep-v15-sft-BF16.gguf -> DiT [Registry] acestep-v15-sft-Q4_K_M.gguf -> DiT [Registry] acestep-v15-sft-Q5_K_M.gguf -> DiT [Registry] acestep-v15-sft-Q6_K.gguf -> DiT [Registry] acestep-v15-sft-Q8_0.gguf -> DiT [Registry] acestep-v15-sftturbo50-BF16.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q4_K_M.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q5_K_M.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q6_K.gguf -> DiT [Registry] acestep-v15-sftturbo50-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-BF16.gguf -> DiT [Registry] acestep-v15-turbo-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-continuous-BF16.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-continuous-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-shift1-BF16.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-shift1-Q8_0.gguf -> DiT [Registry] acestep-v15-turbo-shift3-BF16.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q4_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q5_K_M.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q6_K.gguf -> DiT [Registry] acestep-v15-turbo-shift3-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-base-BF16.gguf -> DiT [Registry] acestep-v15-xl-base-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-base-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-base-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-base-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-sft-BF16.gguf -> DiT [Registry] acestep-v15-xl-sft-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-sft-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-sft-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-sft-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-BF16.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-sftturbo50-Q8_0.gguf -> DiT [Registry] acestep-v15-xl-turbo-BF16.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q4_K_M.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q5_K_M.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q6_K.gguf -> DiT [Registry] acestep-v15-xl-turbo-Q8_0.gguf -> DiT [Registry] scragvae-BF16.gguf -> VAE [Registry] vae-BF16.gguf -> VAE [Store] Created (policy=STRICT) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-sft-BF16.gguf: 830 tensors, data at offset 69312 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-sft-BF16.gguf: 830 tensors, data at offset 69312 [Synth-Load] Ready: turbo=no, fa=no, batch_cfg=yes [Resolve-Params] max audio codes across batch: 434 (86.8s @ 5Hz) [Resolve-T] T=2170, S=1085 [Resolve-T] seed=42, steps=50, guidance=1.0, shift=1.0, duration=88.0s [BPE] Loaded from GGUF: 151643 vocab, 151387 merges ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): Device 0: NVIDIA RTX PRO 6000 Blackwell Workstation Edition, compute capability 12.0, VMM: yes, VRAM: 97247 MiB load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = NVIDIA RTX PRO 6000 Blackwell Workstation Edition (NVIDIA) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2 load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] TextEncoder backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/Qwen3-Embedding-0.6B-BF16.gguf: 310 tensors, data at offset 5337568 [Load] TextEncoder: 28L, H=1024, Nh=16/8 [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 310 tensors, 1136.5 MB into backend [Store] Load TextEnc: 433 ms [Debug] text_hidden: [70, 1024] first4: 3.704526 2.436253 0.222853 -13.131872 [Debug] lyric_embed: [167, 1024] first4: 0.029175 0.032227 -0.022339 -0.028809 [Store] Unload TextEnc (1136.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] CondEncoder backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-sft-BF16.gguf: 830 tensors, data at offset 69312 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 141 tensors, 1160.5 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L, CLS), text_proj, null_cond [Store] Load CondEnc: 795 ms [CondEnc] Lyric sliding mask: 167x167, window=128 [CondEnc] Timbre sliding mask: 2x2, window=128 (CLS) [Encode] Packed: lyric=167 + timbre=1 + text=70 = 238 tokens [Encode-Text Batch0] 70+167 tokens -> enc_S=238, 109.5 ms [Debug] enc_hidden: [238, 2048] first4: 0.686898 -0.019098 -0.051494 0.022655 [Store] Unload CondEnc (1160.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] Detokenizer backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-sft-BF16.gguf: 830 tensors, data at offset 69312 [WeightCtx] Loaded 30 tensors, 200.3 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 112 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 907.5 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.124172 1.435321 0.310164 -0.624504 [Store] Unload FSQ-Detok (200.3 MB) [Init-Noise Batch0] Philox noise seed=42, [2170, 64] solver=euler [Debug] noise: [2170, 64] first4: 0.194336 2.156250 -0.171875 0.847656 [Debug] context: [2170, 128] first4: -0.124172 1.435321 0.310164 -0.624504 [Init-Noise] Starting: T=2170, S=1085, enc_S=238, steps=50, batch=1 (cover) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] DiT backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-sft-BF16.gguf: 830 tensors, data at offset 69312 [DiT] Self-attn: Q+K+V fused [DiT] Cross-attn: Q+K+V fused [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 630 tensors, 7955.6 MB into backend [Load] DiT: 32 layers, H=2560, Nh=32/8, D=128 [Store] Load DiT: 5500 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2825 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [15360] first4: 0.012579 0.105540 0.073639 -0.031893 [Debug] temb: [2560] first4: 0.009506 -0.007716 -0.006105 0.004584 [Debug] temb_t: [2560] first4: 0.007969 -0.007948 -0.006674 0.003606 [Debug] temb_r: [2560] first4: 0.001538 0.000232 0.000569 0.000978 [Debug] sinusoidal_t: [256] first4: 0.562379 0.789627 0.439928 -0.023645 [Debug] sinusoidal_r: [256] first4: 1.000000 1.000000 1.000000 1.000000 [Debug] temb_lin1_t: [2560] first4: 0.032161 -0.082097 0.088242 -0.064953 [Debug] temb_lin1_r: [2560] first4: 0.006956 -0.005390 -0.002806 -0.011722 [Debug] hidden_after_proj_in: [2560, 1085] first4: 0.326588 -0.492784 0.101537 -0.214441 [Debug] proj_in_input: [192, 2170] first4: -0.124172 1.435321 0.310164 -0.624504 [Debug] enc_after_cond_emb: [2560, 238] first4: 0.035580 0.640036 0.108195 0.870601 [Debug] layer0_sa_input: [2560, 1085] first4: 0.036394 -0.019050 0.098659 -0.097736 [Debug] layer0_q_after_rope: [128, 32] first4: -0.273283 -2.149641 0.304081 -0.031929 [Debug] layer0_k_after_rope: [128, 8] first4: 0.727837 2.921756 1.168267 2.043445 [Debug] layer0_sa_output: [2560, 1085] first4: 1.948995 4.407659 -0.829639 7.829544 [Debug] layer0_attn_out: [4096, 1085] first4: 0.457383 -2.189255 -0.516980 -4.126828 [Debug] layer0_after_self_attn: [2560, 1085] first4: 0.457383 -2.189255 -0.516980 -4.126828 [Debug] layer0_after_cross_attn: [2560, 1085] first4: 0.293133 -1.919286 -0.432752 -4.233349 [Debug] hidden_after_layer0: [2560, 1085] first4: -1.838778 -1.227677 248.406464 -3.998169 [Debug] hidden_after_layer6: [2560, 1085] first4: -7.849791 3.649184 316.608185 -21.753986 [Debug] hidden_after_layer12: [2560, 1085] first4: -23.767054 39.786629 233.126083 16.496397 [Debug] hidden_after_layer18: [2560, 1085] first4: 9.557707 -13.310936 234.409912 19.770365 [Debug] hidden_after_layer31: [2560, 1085] first4: 63.386658 -107.207352 7.206509 89.045418 [Debug] dit_step0_vt: [2170, 64] first4: -0.320832 2.211595 0.011690 1.703868 [Debug] dit_step0_xt: [2170, 64] first4: 0.200753 2.112018 -0.172109 0.813579 [DiT] Step 1/50 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.348966 2.148599 0.069170 1.558472 [Debug] dit_step1_xt: [2170, 64] first4: 0.207732 2.069046 -0.173492 0.782409 [DiT] Step 2/50 t=0.980 [Debug] dit_step2_vt: [2170, 64] first4: -0.324729 2.166924 0.050048 1.569666 [Debug] dit_step2_xt: [2170, 64] first4: 0.214226 2.025707 -0.174493 0.751016 [DiT] Step 3/50 t=0.960 [Debug] dit_step3_vt: [2170, 64] first4: -0.279915 2.132787 0.043429 1.569572 [Debug] dit_step3_xt: [2170, 64] first4: 0.219825 1.983052 -0.175362 0.719625 [DiT] Step 4/50 t=0.940 [Debug] dit_step4_vt: [2170, 64] first4: -0.271724 2.066935 0.018875 1.584919 [Debug] dit_step4_xt: [2170, 64] first4: 0.225259 1.941713 -0.175739 0.687926 [DiT] Step 5/50 t=0.920 [Debug] dit_step5_vt: [2170, 64] first4: -0.261195 2.045686 0.028628 1.590381 [Debug] dit_step5_xt: [2170, 64] first4: 0.230483 1.900799 -0.176312 0.656119 [DiT] Step 6/50 t=0.900 [Debug] dit_step6_vt: [2170, 64] first4: -0.252663 2.020672 0.064672 1.609309 [Debug] dit_step6_xt: [2170, 64] first4: 0.235536 1.860386 -0.177605 0.623933 [DiT] Step 7/50 t=0.880 [Debug] dit_step7_vt: [2170, 64] first4: -0.251947 1.982464 0.110063 1.616850 [Debug] dit_step7_xt: [2170, 64] first4: 0.240575 1.820737 -0.179807 0.591596 [DiT] Step 8/50 t=0.860 [Debug] dit_step8_vt: [2170, 64] first4: -0.261629 1.935167 0.136276 1.606429 [Debug] dit_step8_xt: [2170, 64] first4: 0.245808 1.782033 -0.182532 0.559467 [DiT] Step 9/50 t=0.840 [Debug] dit_step9_vt: [2170, 64] first4: -0.284783 1.879064 0.126261 1.603950 [Debug] dit_step9_xt: [2170, 64] first4: 0.251504 1.744452 -0.185057 0.527388 [DiT] Step 10/50 t=0.820 [Debug] dit_step10_vt: [2170, 64] first4: -0.292821 1.834026 0.116344 1.598142 [Debug] dit_step10_xt: [2170, 64] first4: 0.257360 1.707771 -0.187384 0.495425 [DiT] Step 11/50 t=0.800 [Debug] dit_step11_vt: [2170, 64] first4: -0.291175 1.787733 0.105402 1.586314 [Debug] dit_step11_xt: [2170, 64] first4: 0.263184 1.672017 -0.189492 0.463699 [DiT] Step 12/50 t=0.780 [Debug] dit_step12_vt: [2170, 64] first4: -0.284183 1.739205 0.091328 1.571043 [Debug] dit_step12_xt: [2170, 64] first4: 0.268867 1.637233 -0.191319 0.432278 [DiT] Step 13/50 t=0.760 [Debug] dit_step13_vt: [2170, 64] first4: -0.279806 1.689754 0.075029 1.564156 [Debug] dit_step13_xt: [2170, 64] first4: 0.274463 1.603438 -0.192819 0.400995 [DiT] Step 14/50 t=0.740 [Debug] dit_step14_vt: [2170, 64] first4: -0.270989 1.635002 0.058919 1.555878 [Debug] dit_step14_xt: [2170, 64] first4: 0.279883 1.570738 -0.193998 0.369877 [DiT] Step 15/50 t=0.720 [Debug] dit_step15_vt: [2170, 64] first4: -0.263414 1.587634 0.037730 1.552913 [Debug] dit_step15_xt: [2170, 64] first4: 0.285151 1.538985 -0.194752 0.338819 [DiT] Step 16/50 t=0.700 [Debug] dit_step16_vt: [2170, 64] first4: -0.239063 1.540666 0.020305 1.544392 [Debug] dit_step16_xt: [2170, 64] first4: 0.289933 1.508172 -0.195158 0.307931 [DiT] Step 17/50 t=0.680 [Debug] dit_step17_vt: [2170, 64] first4: -0.217356 1.492941 -0.000567 1.538173 [Debug] dit_step17_xt: [2170, 64] first4: 0.294280 1.478313 -0.195147 0.277168 [DiT] Step 18/50 t=0.660 [Debug] dit_step18_vt: [2170, 64] first4: -0.187388 1.441180 -0.010117 1.532847 [Debug] dit_step18_xt: [2170, 64] first4: 0.298028 1.449489 -0.194945 0.246511 [DiT] Step 19/50 t=0.640 [Debug] dit_step19_vt: [2170, 64] first4: -0.152857 1.395026 -0.019611 1.519526 [Debug] dit_step19_xt: [2170, 64] first4: 0.301085 1.421589 -0.194553 0.216120 [DiT] Step 20/50 t=0.620 [Debug] dit_step20_vt: [2170, 64] first4: -0.120875 1.342314 -0.028693 1.515556 [Debug] dit_step20_xt: [2170, 64] first4: 0.303502 1.394742 -0.193979 0.185809 [DiT] Step 21/50 t=0.600 [Debug] dit_step21_vt: [2170, 64] first4: -0.090803 1.291662 -0.041982 1.504874 [Debug] dit_step21_xt: [2170, 64] first4: 0.305318 1.368909 -0.193139 0.155712 [DiT] Step 22/50 t=0.580 [Debug] dit_step22_vt: [2170, 64] first4: -0.067822 1.249906 -0.049376 1.491689 [Debug] dit_step22_xt: [2170, 64] first4: 0.306675 1.343911 -0.192152 0.125878 [DiT] Step 23/50 t=0.560 [Debug] dit_step23_vt: [2170, 64] first4: -0.054683 1.192059 -0.062467 1.474525 [Debug] dit_step23_xt: [2170, 64] first4: 0.307768 1.320070 -0.190902 0.096387 [DiT] Step 24/50 t=0.540 [Debug] dit_step24_vt: [2170, 64] first4: -0.040775 1.141771 -0.068763 1.458413 [Debug] dit_step24_xt: [2170, 64] first4: 0.308584 1.297234 -0.189527 0.067219 [DiT] Step 25/50 t=0.520 [Debug] dit_step25_vt: [2170, 64] first4: -0.029483 1.088625 -0.083457 1.436183 [Debug] dit_step25_xt: [2170, 64] first4: 0.309173 1.275462 -0.187858 0.038495 [DiT] Step 26/50 t=0.500 [Debug] dit_step26_vt: [2170, 64] first4: -0.029674 1.023079 -0.092929 1.415317 [Debug] dit_step26_xt: [2170, 64] first4: 0.309767 1.255000 -0.185999 0.010189 [DiT] Step 27/50 t=0.480 [Debug] dit_step27_vt: [2170, 64] first4: -0.031299 0.961000 -0.105222 1.391265 [Debug] dit_step27_xt: [2170, 64] first4: 0.310393 1.235780 -0.183895 -0.017636 [DiT] Step 28/50 t=0.460 [Debug] dit_step28_vt: [2170, 64] first4: -0.040705 0.896078 -0.120888 1.368112 [Debug] dit_step28_xt: [2170, 64] first4: 0.311207 1.217859 -0.181477 -0.044998 [DiT] Step 29/50 t=0.440 [Debug] dit_step29_vt: [2170, 64] first4: -0.043455 0.822728 -0.129442 1.344672 [Debug] dit_step29_xt: [2170, 64] first4: 0.312076 1.201404 -0.178888 -0.071892 [DiT] Step 30/50 t=0.420 [Debug] dit_step30_vt: [2170, 64] first4: -0.057244 0.749911 -0.148480 1.314000 [Debug] dit_step30_xt: [2170, 64] first4: 0.313221 1.186406 -0.175919 -0.098172 [DiT] Step 31/50 t=0.400 [Debug] dit_step31_vt: [2170, 64] first4: -0.074616 0.669673 -0.157683 1.289025 [Debug] dit_step31_xt: [2170, 64] first4: 0.314713 1.173013 -0.172765 -0.123952 [DiT] Step 32/50 t=0.380 [Debug] dit_step32_vt: [2170, 64] first4: -0.098136 0.582216 -0.168690 1.259541 [Debug] dit_step32_xt: [2170, 64] first4: 0.316676 1.161368 -0.169391 -0.149143 [DiT] Step 33/50 t=0.360 [Debug] dit_step33_vt: [2170, 64] first4: -0.108541 0.503865 -0.173736 1.232660 [Debug] dit_step33_xt: [2170, 64] first4: 0.318847 1.151291 -0.165916 -0.173796 [DiT] Step 34/50 t=0.340 [Debug] dit_step34_vt: [2170, 64] first4: -0.122127 0.412641 -0.184488 1.204758 [Debug] dit_step34_xt: [2170, 64] first4: 0.321289 1.143038 -0.162227 -0.197892 [DiT] Step 35/50 t=0.320 [Debug] dit_step35_vt: [2170, 64] first4: -0.147582 0.307006 -0.180319 1.177333 [Debug] dit_step35_xt: [2170, 64] first4: 0.324241 1.136898 -0.158620 -0.221438 [DiT] Step 36/50 t=0.300 [Debug] dit_step36_vt: [2170, 64] first4: -0.163422 0.213779 -0.176185 1.136736 [Debug] dit_step36_xt: [2170, 64] first4: 0.327509 1.132622 -0.155097 -0.244173 [DiT] Step 37/50 t=0.280 [Debug] dit_step37_vt: [2170, 64] first4: -0.165596 0.120089 -0.176319 1.108003 [Debug] dit_step37_xt: [2170, 64] first4: 0.330821 1.130221 -0.151570 -0.266333 [DiT] Step 38/50 t=0.260 [Debug] dit_step38_vt: [2170, 64] first4: -0.161711 0.012946 -0.159274 1.060183 [Debug] dit_step38_xt: [2170, 64] first4: 0.334056 1.129962 -0.148385 -0.287537 [DiT] Step 39/50 t=0.240 [Debug] dit_step39_vt: [2170, 64] first4: -0.185516 -0.088994 -0.148506 1.029170 [Debug] dit_step39_xt: [2170, 64] first4: 0.337766 1.131742 -0.145415 -0.308120 [DiT] Step 40/50 t=0.220 [Debug] dit_step40_vt: [2170, 64] first4: -0.205416 -0.201278 -0.126516 0.987921 [Debug] dit_step40_xt: [2170, 64] first4: 0.341874 1.135767 -0.142884 -0.327879 [DiT] Step 41/50 t=0.200 [Debug] dit_step41_vt: [2170, 64] first4: -0.231399 -0.307358 -0.103599 0.941756 [Debug] dit_step41_xt: [2170, 64] first4: 0.346502 1.141914 -0.140812 -0.346714 [DiT] Step 42/50 t=0.180 [Debug] dit_step42_vt: [2170, 64] first4: -0.250293 -0.392337 -0.076667 0.897680 [Debug] dit_step42_xt: [2170, 64] first4: 0.351508 1.149761 -0.139279 -0.364667 [DiT] Step 43/50 t=0.160 [Debug] dit_step43_vt: [2170, 64] first4: -0.281178 -0.488656 -0.037671 0.849780 [Debug] dit_step43_xt: [2170, 64] first4: 0.357132 1.159534 -0.138526 -0.381663 [DiT] Step 44/50 t=0.140 [Debug] dit_step44_vt: [2170, 64] first4: -0.308651 -0.578670 0.006148 0.793530 [Debug] dit_step44_xt: [2170, 64] first4: 0.363305 1.171108 -0.138648 -0.397533 [DiT] Step 45/50 t=0.120 [Debug] dit_step45_vt: [2170, 64] first4: -0.343072 -0.653961 0.053503 0.749606 [Debug] dit_step45_xt: [2170, 64] first4: 0.370166 1.184187 -0.139719 -0.412526 [DiT] Step 46/50 t=0.100 [Debug] dit_step46_vt: [2170, 64] first4: -0.384832 -0.727317 0.102161 0.701674 [Debug] dit_step46_xt: [2170, 64] first4: 0.377863 1.198733 -0.141762 -0.426559 [DiT] Step 47/50 t=0.080 [Debug] dit_step47_vt: [2170, 64] first4: -0.434828 -0.801845 0.167274 0.666555 [Debug] dit_step47_xt: [2170, 64] first4: 0.386559 1.214770 -0.145107 -0.439890 [DiT] Step 48/50 t=0.060 [Debug] dit_step48_vt: [2170, 64] first4: -0.491147 -0.865238 0.240552 0.651338 [Debug] dit_step48_xt: [2170, 64] first4: 0.396382 1.232075 -0.149918 -0.452917 [DiT] Step 49/50 t=0.040 [Debug] dit_step49_vt: [2170, 64] first4: -0.489944 -0.850575 0.162132 0.668846 [Debug] dit_x0: [2170, 64] first4: 0.406181 1.249086 -0.153161 -0.466294 [DiT] Step 50/50 t=0.020 [DiT-Generate] Total: 326762.3 ms (326762.3 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.406181 1.249086 -0.153161 -0.466294 [Store] Unload DiT (7955.6 MB) [GGUF] /mnt/workspace/git/acestep.cpp/models/vae-BF16.gguf: 365 tensors, data at offset 30048 load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] VAE backend: CPU (CPU threads: 16) [VAE] Backend: CPU, Weight buffer: 161.1 MB [VAE] Loaded: 5 blocks, upsample=1920x, F32 activations [Store] Load VAE-Dec: 719 ms [VAE] Tiled decode: 3 tiles (chunk=1024, overlap=64, stride=896) [VAE] Graph: 479 nodes, T_latent=960 [VAE] Upsample factor: 1920.00 (expected ~1920) [VAE] Graph: 479 nodes, T_latent=1024 [VAE] Graph: 479 nodes, T_latent=442 [VAE] Tiled decode done: 3 tiles -> T_audio=4166400 (86.80s @ 48kHz) [VAE-Decode Batch0] Decode: 32389.6 ms [Debug] vae_audio: [2, 4166400] first4: -0.001385 -0.000667 -0.000764 -0.000284 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 462 ms (187.69x realtime), 32 threads [MP3] Wrote ggml-xl-sft/request00.mp3 [Ace-Synth] All done 2026-07-12 09:23:18.495 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:174 - [initialize_service] Attempting to load model with attention implementation: sdpa [Python] Generating (acestep-v15-xl-turbo, 8 steps)... Using precomputed LM hints Using precomputed LM hints [Python] Wrote python-xl-turbo/output.wav: 4166400 samples (86.80s @ 48kHz stereo) [Python] Done, 40 dump files [Xl-turbo] Cosine similarities GGML vs Python stage GGML vs Python text_hidden 0.999810 lyric_embed 1.000000 enc_hidden 0.999574 detok_output 0.999996 context 0.999997 noise 1.000000 temb_t 0.999995 hidden_after_proj_in 0.999980 enc_after_cond_emb 0.999693 layer0_sa_output 0.999651 hidden_after_layer0 0.999433 hidden_after_layer6 0.999823 hidden_after_layer12 0.997282 hidden_after_layer18 0.996205 hidden_after_layer31 0.988315 dit_step0_vt 0.912461 dit_step0_xt 0.999842 dit_step1_vt 0.931192 dit_step1_xt 0.999541 dit_step2_vt 0.933803 dit_step2_xt 0.998823 dit_step3_vt 0.929596 dit_step3_xt 0.997086 dit_step4_vt 0.923362 dit_step4_xt 0.992719 dit_step5_vt 0.914847 dit_step5_xt 0.982235 dit_step6_vt 0.907437 dit_step6_xt 0.961513 dit_step7_vt 0.887285 dit_x0 0.927893 vae_audio 0.734169 vae_audio (STFT cosine) 0.923323 [Xl-turbo] Error growth GGML vs Python stage cos max_err mean_err mean_A std_A mean_B std_B dit_step0_xt 0.999842 0.159259 0.012448 -0.002991 0.978362 -0.002721 0.976534 dit_step1_xt 0.999541 0.371954 0.021009 -0.005948 0.952133 -0.005567 0.949004 dit_step2_xt 0.998823 0.545209 0.032087 -0.009744 0.923230 -0.009330 0.918931 dit_step3_xt 0.997086 0.809188 0.047817 -0.015394 0.891898 -0.014418 0.887241 dit_step4_xt 0.992719 1.177347 0.072342 -0.023152 0.862755 -0.021453 0.857796 dit_step5_xt 0.982235 1.745782 0.110621 -0.034669 0.846415 -0.032240 0.840033 dit_step6_xt 0.961513 2.505169 0.168418 -0.051763 0.870650 -0.049194 0.863964 [Xl-sft] steps=50, shift=1.0 | acestep-v15-xl-sft-BF16.gguf [GGML] Running acestep-v15-xl-sft-BF16.gguf... [GGML] Done, 131 dump files [Python] Initializing acestep-v15-xl-sft... Loading checkpoint shards: 0%| | 0/4 [00:00 2026-07-12 09:23:22.068 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 09:23:22.068 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:124 - lyrics_text: # Languages fr # Lyric # Lyric [Intro - Guitar Riff] [Verse 1] Dans le monde des tutos virtuels G ta toise en nouvelle passion Avec Ggendoline et PumbΓ© Γ  midi La communautΓ©, c'est l'unitΓ© Quel joie, une clΓ© [Chorus] Dans le monde des tutos virtuels GΓ’ndoline et PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner [Guitar Solo] [Verse 2] Dans le monde des tutos virtuels GΓ’ndoline, PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner<|endoftext|> 2026-07-12 09:23:22.068 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 09:23:22.071 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 09:23:22.079 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 09:23:22.079 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 09:23:22.086 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)... [Python] Generating (acestep-v15-xl-sft, 50 steps)... Using precomputed LM hints Using precomputed LM hints 0%| | 0/50 [00:00