[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-Q8_0.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-Q8_0.gguf: 678 tensors, data at offset 56864 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-turbo-Q8_0.gguf: 678 tensors, data at offset 56864 [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: 303 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-Q8_0.gguf: 678 tensors, data at offset 56864 [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, 616.6 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L), text_proj, null_cond [Store] Load CondEnc: 339 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, 136.0 ms [Debug] enc_hidden: [238, 2048] first4: 1.758412 -0.049824 -0.132638 0.057941 [Store] Unload CondEnc (616.6 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-Q8_0.gguf: 678 tensors, data at offset 56864 [WeightCtx] Loaded 30 tensors, 106.5 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 188 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 496.0 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.126218 1.441045 0.305219 -0.629688 [Store] Unload FSQ-Detok (106.5 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: -0.126218 1.441045 0.305219 -0.629688 [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-Q8_0.gguf: 678 tensors, data at offset 56864 [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, 1600.7 MB into backend [Load] DiT: 24 layers, H=2048, Nh=16/8, D=128 [Store] Load DiT: 988 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: 0.259485 -0.161550 -0.096885 0.051766 [Debug] temb: [2048] first4: 0.000214 -0.132557 -0.035428 0.064847 [Debug] temb_t: [2048] first4: 0.001194 0.026823 -0.052744 0.063762 [Debug] temb_r: [2048] first4: -0.000980 -0.159380 0.017316 0.001084 [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: -0.049228 -0.051913 -0.015026 -0.038076 [Debug] temb_lin1_r: [2048] first4: -0.013066 -0.018835 -0.015731 0.008462 [Debug] hidden_after_proj_in: [2048, 1085] first4: -1.038249 -0.957445 0.537078 0.447006 [Debug] proj_in_input: [192, 2170] first4: -0.126218 1.441045 0.305219 -0.629688 [Debug] enc_after_cond_emb: [2048, 238] first4: -0.174778 0.815771 0.331865 -0.559953 [Debug] layer0_sa_input: [2048, 1085] first4: -0.718529 -0.757126 -0.047071 0.261381 [Debug] layer0_q_after_rope: [128, 16] first4: -1.544202 -1.032205 0.191246 0.456493 [Debug] layer0_k_after_rope: [128, 8] first4: -0.174778 0.815771 0.331865 -0.559953 [Debug] layer0_sa_output: [2048, 1085] first4: -1.514885 0.168405 -0.354086 0.508003 [Debug] layer0_attn_out: [2048, 1085] first4: -1.544202 -1.032205 0.191246 0.456493 [Debug] layer0_after_self_attn: [2048, 1085] first4: -1.544202 -1.032205 0.191246 0.456493 [Debug] layer0_after_cross_attn: [2048, 1085] first4: -1.596852 -0.819318 -0.283829 0.491399 [Debug] hidden_after_layer0: [2048, 1085] first4: -9.076782 0.569024 52.384930 -0.865368 [Debug] hidden_after_layer6: [2048, 1085] first4: -21.564232 0.242397 33.815739 -4.188777 [Debug] hidden_after_layer12: [2048, 1085] first4: -14.881989 -18.805410 69.848145 28.630205 [Debug] hidden_after_layer18: [2048, 1085] first4: -26.210476 15.271601 58.086185 21.408840 [Debug] hidden_after_layer23: [2048, 1085] first4: -4.709541 41.288780 192.847153 148.677338 [Debug] dit_step0_vt: [2170, 64] first4: 0.016164 1.116295 0.320523 2.375249 [Debug] dit_step0_xt: [2170, 64] first4: 0.193601 2.105509 -0.186444 0.739690 [DiT] Step 1/8 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.193502 1.360758 -0.151318 1.857501 [Debug] dit_step1_xt: [2170, 64] first4: 0.204156 2.031286 -0.178191 0.638372 [DiT] Step 2/8 t=0.955 [Debug] dit_step2_vt: [2170, 64] first4: -0.016619 1.241479 0.111612 2.392810 [Debug] dit_step2_xt: [2170, 64] first4: 0.205264 1.948521 -0.185631 0.478851 [DiT] Step 3/8 t=0.900 [Debug] dit_step3_vt: [2170, 64] first4: 0.250226 1.084855 0.270988 2.656159 [Debug] dit_step3_xt: [2170, 64] first4: 0.184412 1.858116 -0.208214 0.257505 [DiT] Step 4/8 t=0.833 [Debug] dit_step4_vt: [2170, 64] first4: 0.281901 1.035304 0.111452 2.713949 [Debug] dit_step4_xt: [2170, 64] first4: 0.154208 1.747191 -0.220155 -0.033275 [DiT] Step 5/8 t=0.750 [Debug] dit_step5_vt: [2170, 64] first4: 0.264211 0.928700 -0.288185 2.749583 [Debug] dit_step5_xt: [2170, 64] first4: 0.116463 1.614520 -0.178986 -0.426073 [DiT] Step 6/8 t=0.643 [Debug] dit_step6_vt: [2170, 64] first4: 0.173657 0.643419 -0.835215 2.794378 [Debug] dit_step6_xt: [2170, 64] first4: 0.081732 1.485836 -0.011943 -0.984949 [DiT] Step 7/8 t=0.500 [Debug] dit_step7_vt: [2170, 64] first4: -0.009575 0.263735 -1.486802 3.090469 [Debug] dit_x0: [2170, 64] first4: 0.084605 1.406715 0.434098 -1.912089 [DiT] Step 8/8 t=0.300 [DiT-Generate] Total: 29191.3 ms (29191.3 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.084605 1.406715 0.434098 -1.912089 [Store] Unload DiT (1600.7 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: 711 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: 27479.1 ms [Debug] vae_audio: [2, 4166400] first4: 0.000664 0.001383 0.001160 0.001688 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 496 ms (174.91x realtime), 32 threads [MP3] Wrote ggml-turbo/request00.mp3 [Ace-Synth] All done 2026-07-12 08:29:19.912 | 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 08:29:22.056 | WARNING | acestep.training.trainer::40 - bitsandbytes not installed. Using standard AdamW. 2026-07-12 08:29:22.061 | 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 08:29:22.141 | 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 08:29:23.686 | 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 08:29:23.686 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 08:29:23.686 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 08:29:23.687 | 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 08:29:23.690 | INFO | acestep.core.generation.handler.generate_music:_vram_preflight_check:156 - [generate_music] VRAM pre-flight: 88.44 GB free, ~0.94 GB needed (batch=1, duration=88s, mode=turbo). 2026-07-12 08:29:23.695 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 08:29:23.907 | 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 08:29:23.908 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 08:29:23.909 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 08:29:23.909 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 08:29:23.909 | 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 08:29:23.909 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 08:29:23.909 | 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 08:29:23.909 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 08:29:23.916 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 08:29:23.930 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 08:29:23.930 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 08:29:23.956 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)... 2026-07-12 08:29:23.963 | 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 08:29:24.051 | 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 08:29:24.275 | INFO | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:42 - [generate_music] Model generation completed. Decoding latents... 2026-07-12 08:29:24.276 | 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 08:29:24.276 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:65 - [generate_music] time_costs: {'encoder_time_cost': 0.006937742233276367, 'diffusion_time_cost': 0.3117344379425049, 'diffusion_per_step_time_cost': 0.03896680474281311, 'total_time_cost': 0.31867218017578125, 'offload_time_cost': 0.0} 2026-07-12 08:29:24.290 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:127 - [generate_music] Decoding latents with VAE... 2026-07-12 08:29:24.292 | 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 08:29:24.292 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:154 - [generate_music] Effective free VRAM before VAE decode: 88.34 GB 2026-07-12 08:29:24.292 | 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 08:29:24.292 | DEBUG | acestep.core.generation.handler.memory_utils:_get_auto_decode_chunk_size:108 - [_get_auto_decode_chunk_size] Effective free VRAM: 88.34 GB 2026-07-12 08:29:24.292 | DEBUG | acestep.core.generation.handler.memory_utils:_should_offload_wav_to_cpu:131 - [_should_offload_wav_to_cpu] Effective free VRAM: 88.34 GB 2026-07-12 08:29:24.292 | 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 08:29:24.588 | 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 08:29:24.752 | 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 08:29:24.755 | 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-Q8_0.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-Q8_0.gguf: 678 tensors, data at offset 56800 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-sft-Q8_0.gguf: 678 tensors, data at offset 56800 [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: 254 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-Q8_0.gguf: 678 tensors, data at offset 56800 [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, 616.6 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L), text_proj, null_cond [Store] Load CondEnc: 387 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, 137.5 ms [Debug] enc_hidden: [238, 2048] first4: 1.758412 -0.049824 -0.132638 0.057941 [Store] Unload CondEnc (616.6 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-Q8_0.gguf: 678 tensors, data at offset 56800 [WeightCtx] Loaded 30 tensors, 106.5 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 178 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 493.9 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.126218 1.441045 0.305219 -0.629688 [Store] Unload FSQ-Detok (106.5 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: -0.126218 1.441045 0.305219 -0.629688 [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-Q8_0.gguf: 678 tensors, data at offset 56800 [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, 1600.7 MB into backend [Load] DiT: 24 layers, H=2048, Nh=16/8, D=128 [Store] Load DiT: 1122 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: 0.155643 -0.115659 -0.086888 0.081457 [Debug] temb: [2048] first4: -0.002814 -0.176488 0.004230 -0.002015 [Debug] temb_t: [2048] first4: -0.001218 0.003344 -0.013065 -0.002081 [Debug] temb_r: [2048] first4: -0.001596 -0.179832 0.017296 0.000066 [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: -0.038611 0.029679 0.028318 -0.024159 [Debug] temb_lin1_r: [2048] first4: 0.001863 0.003353 -0.000552 -0.000197 [Debug] hidden_after_proj_in: [2048, 1085] first4: -1.088787 -0.914308 0.499170 0.440692 [Debug] proj_in_input: [192, 2170] first4: -0.126218 1.441045 0.305219 -0.629688 [Debug] enc_after_cond_emb: [2048, 238] first4: -0.193547 0.871285 0.327645 -0.583599 [Debug] layer0_sa_input: [2048, 1085] first4: -0.912407 -0.708866 -0.037435 0.293606 [Debug] layer0_q_after_rope: [128, 16] first4: -1.802147 -1.365389 -0.120474 0.380596 [Debug] layer0_k_after_rope: [128, 8] first4: -0.193547 0.871285 0.327645 -0.583599 [Debug] layer0_sa_output: [2048, 1085] first4: -1.649812 0.797531 -0.549257 0.536640 [Debug] layer0_attn_out: [2048, 1085] first4: -1.802147 -1.365389 -0.120474 0.380596 [Debug] layer0_after_self_attn: [2048, 1085] first4: -1.802147 -1.365389 -0.120474 0.380596 [Debug] layer0_after_cross_attn: [2048, 1085] first4: -1.959073 -1.027594 -0.397269 0.384385 [Debug] hidden_after_layer0: [2048, 1085] first4: -9.420540 1.180536 57.404362 -1.597696 [Debug] hidden_after_layer6: [2048, 1085] first4: -17.385201 4.430685 58.665813 -2.951168 [Debug] hidden_after_layer12: [2048, 1085] first4: -11.284355 4.942255 -19.330605 -2.780930 [Debug] hidden_after_layer18: [2048, 1085] first4: -3.720545 19.587526 -35.580078 -11.202410 [Debug] hidden_after_layer23: [2048, 1085] first4: 34.085365 65.913452 61.195549 -7.649443 [Debug] dit_step0_vt: [2170, 64] first4: -0.573803 2.549292 -0.174947 1.459109 [Debug] dit_step0_xt: [2170, 64] first4: 0.205812 2.105264 -0.168376 0.818474 [DiT] Step 1/50 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.645159 2.545997 0.004436 1.296897 [Debug] dit_step1_xt: [2170, 64] first4: 0.218715 2.054344 -0.168465 0.792536 [DiT] Step 2/50 t=0.980 [Debug] dit_step2_vt: [2170, 64] first4: -0.639208 2.496887 0.038706 1.310340 [Debug] dit_step2_xt: [2170, 64] first4: 0.231499 2.004406 -0.169239 0.766329 [DiT] Step 3/50 t=0.960 [Debug] dit_step3_vt: [2170, 64] first4: -0.626352 2.447198 0.032850 1.319771 [Debug] dit_step3_xt: [2170, 64] first4: 0.244026 1.955463 -0.169896 0.739934 [DiT] Step 4/50 t=0.940 [Debug] dit_step4_vt: [2170, 64] first4: -0.555068 2.353463 0.029818 1.309741 [Debug] dit_step4_xt: [2170, 64] first4: 0.255128 1.908393 -0.170492 0.713739 [DiT] Step 5/50 t=0.920 [Debug] dit_step5_vt: [2170, 64] first4: -0.519853 2.275097 0.001329 1.286966 [Debug] dit_step5_xt: [2170, 64] first4: 0.265525 1.862891 -0.170519 0.688000 [DiT] Step 6/50 t=0.900 [Debug] dit_step6_vt: [2170, 64] first4: -0.476843 2.217056 -0.025233 1.296081 [Debug] dit_step6_xt: [2170, 64] first4: 0.275062 1.818550 -0.170014 0.662078 [DiT] Step 7/50 t=0.880 [Debug] dit_step7_vt: [2170, 64] first4: -0.447000 2.156301 -0.046777 1.265486 [Debug] dit_step7_xt: [2170, 64] first4: 0.284002 1.775424 -0.169079 0.636769 [DiT] Step 8/50 t=0.860 [Debug] dit_step8_vt: [2170, 64] first4: -0.387715 2.055564 -0.052714 1.242817 [Debug] dit_step8_xt: [2170, 64] first4: 0.291756 1.734313 -0.168024 0.611912 [DiT] Step 9/50 t=0.840 [Debug] dit_step9_vt: [2170, 64] first4: -0.327880 1.962937 -0.053383 1.228035 [Debug] dit_step9_xt: [2170, 64] first4: 0.298314 1.695054 -0.166957 0.587351 [DiT] Step 10/50 t=0.820 [Debug] dit_step10_vt: [2170, 64] first4: -0.267809 1.876237 -0.038295 1.226301 [Debug] dit_step10_xt: [2170, 64] first4: 0.303670 1.657529 -0.166191 0.562825 [DiT] Step 11/50 t=0.800 [Debug] dit_step11_vt: [2170, 64] first4: -0.235644 1.812230 -0.046852 1.229588 [Debug] dit_step11_xt: [2170, 64] first4: 0.308383 1.621285 -0.165254 0.538234 [DiT] Step 12/50 t=0.780 [Debug] dit_step12_vt: [2170, 64] first4: -0.205502 1.748946 -0.060904 1.203737 [Debug] dit_step12_xt: [2170, 64] first4: 0.312493 1.586306 -0.164036 0.514159 [DiT] Step 13/50 t=0.760 [Debug] dit_step13_vt: [2170, 64] first4: -0.195648 1.658799 -0.073467 1.206374 [Debug] dit_step13_xt: [2170, 64] first4: 0.316406 1.553130 -0.162566 0.490031 [DiT] Step 14/50 t=0.740 [Debug] dit_step14_vt: [2170, 64] first4: -0.180158 1.597013 -0.096607 1.176015 [Debug] dit_step14_xt: [2170, 64] first4: 0.320009 1.521190 -0.160634 0.466511 [DiT] Step 15/50 t=0.720 [Debug] dit_step15_vt: [2170, 64] first4: -0.196391 1.504632 -0.125093 1.145564 [Debug] dit_step15_xt: [2170, 64] first4: 0.323937 1.491097 -0.158132 0.443600 [DiT] Step 16/50 t=0.700 [Debug] dit_step16_vt: [2170, 64] first4: -0.180535 1.428227 -0.145792 1.147970 [Debug] dit_step16_xt: [2170, 64] first4: 0.327547 1.462532 -0.155217 0.420640 [DiT] Step 17/50 t=0.680 [Debug] dit_step17_vt: [2170, 64] first4: -0.205499 1.352937 -0.169683 1.128811 [Debug] dit_step17_xt: [2170, 64] first4: 0.331657 1.435474 -0.151823 0.398064 [DiT] Step 18/50 t=0.660 [Debug] dit_step18_vt: [2170, 64] first4: -0.207817 1.261377 -0.211675 1.106355 [Debug] dit_step18_xt: [2170, 64] first4: 0.335814 1.410246 -0.147589 0.375937 [DiT] Step 19/50 t=0.640 [Debug] dit_step19_vt: [2170, 64] first4: -0.227330 1.176153 -0.222775 1.067168 [Debug] dit_step19_xt: [2170, 64] first4: 0.340360 1.386723 -0.143134 0.354594 [DiT] Step 20/50 t=0.620 [Debug] dit_step20_vt: [2170, 64] first4: -0.247702 1.081392 -0.240563 1.060618 [Debug] dit_step20_xt: [2170, 64] first4: 0.345314 1.365095 -0.138323 0.333381 [DiT] Step 21/50 t=0.600 [Debug] dit_step21_vt: [2170, 64] first4: -0.245698 1.009554 -0.256118 1.045029 [Debug] dit_step21_xt: [2170, 64] first4: 0.350228 1.344904 -0.133200 0.312481 [DiT] Step 22/50 t=0.580 [Debug] dit_step22_vt: [2170, 64] first4: -0.296614 0.916811 -0.256166 1.038846 [Debug] dit_step22_xt: [2170, 64] first4: 0.356161 1.326568 -0.128077 0.291704 [DiT] Step 23/50 t=0.560 [Debug] dit_step23_vt: [2170, 64] first4: -0.310686 0.801235 -0.280401 0.987383 [Debug] dit_step23_xt: [2170, 64] first4: 0.362374 1.310543 -0.122469 0.271956 [DiT] Step 24/50 t=0.540 [Debug] dit_step24_vt: [2170, 64] first4: -0.326664 0.711247 -0.280467 0.956102 [Debug] dit_step24_xt: [2170, 64] first4: 0.368908 1.296318 -0.116860 0.252834 [DiT] Step 25/50 t=0.520 [Debug] dit_step25_vt: [2170, 64] first4: -0.363719 0.575427 -0.281427 0.942674 [Debug] dit_step25_xt: [2170, 64] first4: 0.376182 1.284810 -0.111231 0.233981 [DiT] Step 26/50 t=0.500 [Debug] dit_step26_vt: [2170, 64] first4: -0.400494 0.475536 -0.261690 0.905569 [Debug] dit_step26_xt: [2170, 64] first4: 0.384192 1.275299 -0.105997 0.215869 [DiT] Step 27/50 t=0.480 [Debug] dit_step27_vt: [2170, 64] first4: -0.429878 0.359205 -0.284482 0.880842 [Debug] dit_step27_xt: [2170, 64] first4: 0.392789 1.268115 -0.100308 0.198252 [DiT] Step 28/50 t=0.460 [Debug] dit_step28_vt: [2170, 64] first4: -0.442096 0.237171 -0.275339 0.894205 [Debug] dit_step28_xt: [2170, 64] first4: 0.401631 1.263371 -0.094801 0.180368 [DiT] Step 29/50 t=0.440 [Debug] dit_step29_vt: [2170, 64] first4: -0.472145 0.140859 -0.250299 0.860467 [Debug] dit_step29_xt: [2170, 64] first4: 0.411074 1.260554 -0.089795 0.163159 [DiT] Step 30/50 t=0.420 [Debug] dit_step30_vt: [2170, 64] first4: -0.490643 0.008748 -0.231294 0.846514 [Debug] dit_step30_xt: [2170, 64] first4: 0.420887 1.260379 -0.085169 0.146229 [DiT] Step 31/50 t=0.400 [Debug] dit_step31_vt: [2170, 64] first4: -0.523406 -0.089459 -0.225063 0.841720 [Debug] dit_step31_xt: [2170, 64] first4: 0.431355 1.262169 -0.080668 0.129394 [DiT] Step 32/50 t=0.380 [Debug] dit_step32_vt: [2170, 64] first4: -0.525008 -0.215634 -0.223279 0.800874 [Debug] dit_step32_xt: [2170, 64] first4: 0.441855 1.266481 -0.076202 0.113377 [DiT] Step 33/50 t=0.360 [Debug] dit_step33_vt: [2170, 64] first4: -0.540027 -0.344973 -0.229107 0.775777 [Debug] dit_step33_xt: [2170, 64] first4: 0.452656 1.273381 -0.071620 0.097861 [DiT] Step 34/50 t=0.340 [Debug] dit_step34_vt: [2170, 64] first4: -0.539389 -0.414935 -0.196101 0.735828 [Debug] dit_step34_xt: [2170, 64] first4: 0.463444 1.281679 -0.067698 0.083145 [DiT] Step 35/50 t=0.320 [Debug] dit_step35_vt: [2170, 64] first4: -0.543041 -0.520503 -0.162045 0.727422 [Debug] dit_step35_xt: [2170, 64] first4: 0.474305 1.292089 -0.064457 0.068596 [DiT] Step 36/50 t=0.300 [Debug] dit_step36_vt: [2170, 64] first4: -0.564034 -0.640578 -0.146431 0.688661 [Debug] dit_step36_xt: [2170, 64] first4: 0.485585 1.304901 -0.061528 0.054823 [DiT] Step 37/50 t=0.280 [Debug] dit_step37_vt: [2170, 64] first4: -0.561047 -0.736726 -0.137740 0.664013 [Debug] dit_step37_xt: [2170, 64] first4: 0.496806 1.319635 -0.058774 0.041543 [DiT] Step 38/50 t=0.260 [Debug] dit_step38_vt: [2170, 64] first4: -0.569942 -0.808181 -0.107369 0.604986 [Debug] dit_step38_xt: [2170, 64] first4: 0.508205 1.335799 -0.056626 0.029443 [DiT] Step 39/50 t=0.240 [Debug] dit_step39_vt: [2170, 64] first4: -0.578072 -0.898412 -0.044561 0.572575 [Debug] dit_step39_xt: [2170, 64] first4: 0.519766 1.353767 -0.055735 0.017992 [DiT] Step 40/50 t=0.220 [Debug] dit_step40_vt: [2170, 64] first4: -0.553031 -0.948851 -0.007005 0.551746 [Debug] dit_step40_xt: [2170, 64] first4: 0.530827 1.372744 -0.055595 0.006957 [DiT] Step 41/50 t=0.200 [Debug] dit_step41_vt: [2170, 64] first4: -0.557202 -1.029642 0.021812 0.478962 [Debug] dit_step41_xt: [2170, 64] first4: 0.541971 1.393337 -0.056031 -0.002622 [DiT] Step 42/50 t=0.180 [Debug] dit_step42_vt: [2170, 64] first4: -0.542475 -1.104933 0.076935 0.433945 [Debug] dit_step42_xt: [2170, 64] first4: 0.552821 1.415436 -0.057570 -0.011301 [DiT] Step 43/50 t=0.160 [Debug] dit_step43_vt: [2170, 64] first4: -0.519350 -1.135036 0.116268 0.397006 [Debug] dit_step43_xt: [2170, 64] first4: 0.563208 1.438136 -0.059895 -0.019241 [DiT] Step 44/50 t=0.140 [Debug] dit_step44_vt: [2170, 64] first4: -0.484995 -1.191023 0.137183 0.336048 [Debug] dit_step44_xt: [2170, 64] first4: 0.572907 1.461957 -0.062639 -0.025962 [DiT] Step 45/50 t=0.120 [Debug] dit_step45_vt: [2170, 64] first4: -0.472534 -1.231883 0.182651 0.280380 [Debug] dit_step45_xt: [2170, 64] first4: 0.582358 1.486595 -0.066292 -0.031570 [DiT] Step 46/50 t=0.100 [Debug] dit_step46_vt: [2170, 64] first4: -0.458992 -1.288572 0.203108 0.251294 [Debug] dit_step46_xt: [2170, 64] first4: 0.591538 1.512366 -0.070354 -0.036596 [DiT] Step 47/50 t=0.080 [Debug] dit_step47_vt: [2170, 64] first4: -0.423617 -1.298620 0.215141 0.205778 [Debug] dit_step47_xt: [2170, 64] first4: 0.600010 1.538338 -0.074657 -0.040711 [DiT] Step 48/50 t=0.060 [Debug] dit_step48_vt: [2170, 64] first4: -0.375378 -1.339885 0.234107 0.166782 [Debug] dit_step48_xt: [2170, 64] first4: 0.607518 1.565136 -0.079339 -0.044047 [DiT] Step 49/50 t=0.040 [Debug] dit_step49_vt: [2170, 64] first4: -0.398899 -1.367075 0.228481 0.161776 [Debug] dit_x0: [2170, 64] first4: 0.615496 1.592478 -0.083909 -0.047283 [DiT] Step 50/50 t=0.020 [DiT-Generate] Total: 184781.5 ms (184781.5 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.615496 1.592478 -0.083909 -0.047283 [Store] Unload DiT (1600.7 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: 706 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: 29819.1 ms [Debug] vae_audio: [2, 4166400] first4: -0.001519 -0.000980 -0.001241 -0.000832 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 439 ms (197.73x realtime), 32 threads [MP3] Wrote ggml-sft/request00.mp3 [Ace-Synth] All done 2026-07-12 08:33:04.219 | 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 08:33:05.295 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 08:33:05.295 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 08:33:05.295 | 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 08:33:05.298 | INFO | acestep.core.generation.handler.generate_music:_vram_preflight_check:156 - [generate_music] VRAM pre-flight: 82.30 GB free, ~0.94 GB needed (batch=1, duration=88s, mode=turbo). 2026-07-12 08:33:05.303 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 08:33:05.308 | 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 08:33:05.310 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 08:33:05.310 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 08:33:05.310 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 08:33:05.310 | 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 08:33:05.310 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 08:33:05.310 | 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 08:33:05.310 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 08:33:05.313 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 08:33:05.321 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 08:33:05.321 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 08:33:05.328 | 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-Q8_0.gguf [GGML] Running acestep-v15-turbo-Q8_0.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 0.999811 detok_output 0.999983 context 0.999990 noise 1.000000 temb_t 0.999997 hidden_after_proj_in 0.999985 enc_after_cond_emb 0.999790 layer0_sa_output 0.999925 hidden_after_layer0 0.999955 hidden_after_layer6 0.999890 hidden_after_layer12 0.999341 hidden_after_layer18 0.996784 hidden_after_layer23 0.993886 dit_step0_vt 0.976465 dit_step0_xt 0.999948 dit_step1_vt 0.978674 dit_step1_xt 0.999831 dit_step2_vt 0.980743 dit_step2_xt 0.999545 dit_step3_vt 0.982345 dit_step3_xt 0.998910 dit_step4_vt 0.981068 dit_step4_xt 0.997490 dit_step5_vt 0.978689 dit_step5_xt 0.994358 dit_step6_vt 0.975875 dit_step6_xt 0.988462 dit_step7_vt 0.970037 dit_x0 0.979746 vae_audio 0.902395 vae_audio (STFT cosine) 0.975871 [Turbo] Error growth GGML vs Python stage cos max_err mean_err mean_A std_A mean_B std_B dit_step0_xt 0.999948 0.136893 0.006566 -0.002309 0.972910 -0.002342 0.972003 dit_step1_xt 0.999831 0.268167 0.011368 -0.005308 0.942667 -0.005313 0.941730 dit_step2_xt 0.999545 0.451272 0.017690 -0.009356 0.909159 -0.009311 0.908527 dit_step3_xt 0.998910 0.623028 0.026157 -0.014727 0.873777 -0.014577 0.873624 dit_step4_xt 0.997490 0.757370 0.037950 -0.021793 0.841943 -0.021660 0.841995 dit_step5_xt 0.994358 1.235104 0.055394 -0.031907 0.825216 -0.032109 0.824593 dit_step6_xt 0.988462 2.109199 0.081805 -0.046226 0.856172 -0.046482 0.855546 [SFT] steps=50, shift=1.0 | acestep-v15-sft-Q8_0.gguf [GGML] Running acestep-v15-sft-Q8_0.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-Q8_0.gguf: 830 tensors, data at offset 69088 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-turbo-Q8_0.gguf: 830 tensors, data at offset 69088 [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: 287 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-Q8_0.gguf: 830 tensors, data at offset 69088 [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, 616.6 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L, CLS), text_proj, null_cond [Store] Load CondEnc: 327 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, 136.1 ms [Debug] enc_hidden: [238, 2048] first4: 0.686937 -0.019156 -0.051555 0.022736 [Store] Unload CondEnc (616.6 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-Q8_0.gguf: 830 tensors, data at offset 69088 [WeightCtx] Loaded 30 tensors, 106.5 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 184 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 498.2 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.126218 1.441045 0.305219 -0.629688 [Store] Unload FSQ-Detok (106.5 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: -0.126218 1.441045 0.305219 -0.629688 [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-Q8_0.gguf: 830 tensors, data at offset 69088 [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, 4230.2 MB into backend [Load] DiT: 32 layers, H=2560, Nh=32/8, D=128 [Store] Load DiT: 2952 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: 0.014266 0.109556 0.062634 -0.073523 [Debug] temb: [2560] first4: 0.026310 -0.023038 -0.016457 0.047174 [Debug] temb_t: [2560] first4: 0.014577 -0.022289 -0.020778 0.048747 [Debug] temb_r: [2560] first4: 0.011734 -0.000750 0.004320 -0.001573 [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: 0.063855 -0.019018 0.138265 -0.113400 [Debug] temb_lin1_r: [2560] first4: -0.009850 0.016687 -0.018316 0.012019 [Debug] hidden_after_proj_in: [2560, 1085] first4: 0.343503 -0.578708 0.229538 -0.188917 [Debug] proj_in_input: [192, 2170] first4: -0.126218 1.441045 0.305219 -0.629688 [Debug] enc_after_cond_emb: [2560, 238] first4: 0.033626 0.652631 0.104875 0.873484 [Debug] layer0_sa_input: [2560, 1085] first4: 0.038285 -0.044974 0.091055 -0.133569 [Debug] layer0_q_after_rope: [128, 32] first4: -0.247461 -2.091876 0.384566 0.186698 [Debug] layer0_k_after_rope: [128, 8] first4: 0.047066 2.194061 0.717729 0.543003 [Debug] layer0_sa_output: [2560, 1085] first4: 1.657912 4.301758 -0.556244 5.407282 [Debug] layer0_attn_out: [4096, 1085] first4: 0.475920 -2.241682 -0.178413 -2.789976 [Debug] layer0_after_self_attn: [2560, 1085] first4: 0.475920 -2.241682 -0.178413 -2.789976 [Debug] layer0_after_cross_attn: [2560, 1085] first4: 0.345974 -1.993592 -0.006429 -3.749107 [Debug] hidden_after_layer0: [2560, 1085] first4: 1.804472 -2.444469 242.960587 -3.724934 [Debug] hidden_after_layer6: [2560, 1085] first4: -6.034281 -2.066730 322.203918 -12.083220 [Debug] hidden_after_layer12: [2560, 1085] first4: -11.142314 29.289898 266.120270 28.363281 [Debug] hidden_after_layer18: [2560, 1085] first4: 40.990978 14.105978 281.993073 4.307903 [Debug] hidden_after_layer31: [2560, 1085] first4: -70.006760 -234.297440 -142.338470 176.211655 [Debug] dit_step0_vt: [2170, 64] first4: -1.173317 1.536785 0.459121 1.214168 [Debug] dit_step0_xt: [2170, 64] first4: 0.247669 2.086396 -0.192744 0.792467 [DiT] Step 1/8 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.738895 2.518730 0.820126 1.143052 [Debug] dit_step1_xt: [2170, 64] first4: 0.287972 1.949011 -0.237478 0.730118 [DiT] Step 2/8 t=0.955 [Debug] dit_step2_vt: [2170, 64] first4: -1.327028 2.197412 1.080437 0.810174 [Debug] dit_step2_xt: [2170, 64] first4: 0.376440 1.802517 -0.309507 0.676107 [DiT] Step 3/8 t=0.900 [Debug] dit_step3_vt: [2170, 64] first4: -1.411824 2.003973 1.431707 0.894274 [Debug] dit_step3_xt: [2170, 64] first4: 0.494092 1.635519 -0.428816 0.601584 [DiT] Step 4/8 t=0.833 [Debug] dit_step4_vt: [2170, 64] first4: 0.286396 2.577589 1.076522 0.714767 [Debug] dit_step4_xt: [2170, 64] first4: 0.463407 1.359349 -0.544158 0.525002 [DiT] Step 5/8 t=0.750 [Debug] dit_step5_vt: [2170, 64] first4: -1.130159 1.950145 0.776051 0.448675 [Debug] dit_step5_xt: [2170, 64] first4: 0.624858 1.080757 -0.655023 0.460906 [DiT] Step 6/8 t=0.643 [Debug] dit_step6_vt: [2170, 64] first4: -1.152487 1.987727 0.571347 0.677332 [Debug] dit_step6_xt: [2170, 64] first4: 0.855356 0.683211 -0.769292 0.325439 [DiT] Step 7/8 t=0.500 [Debug] dit_step7_vt: [2170, 64] first4: -1.141325 1.594987 0.741754 0.646256 [Debug] dit_x0: [2170, 64] first4: 1.197753 0.204715 -0.991818 0.131562 [DiT] Step 8/8 t=0.300 [DiT-Generate] Total: 81106.7 ms (81106.7 ms/sample) [Debug] dit_output: [2170, 64] first4: 1.197753 0.204715 -0.991818 0.131562 [Store] Unload DiT (4230.2 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: 717 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: 27165.6 ms [Debug] vae_audio: [2, 4166400] first4: 0.001700 0.004286 0.004426 0.003799 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 492 ms (176.41x realtime), 32 threads [MP3] Wrote ggml-xl-turbo/request00.mp3 [Ace-Synth] All done 2026-07-12 08:35:02.575 | 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 0.999811 detok_output 0.999983 context 0.999990 noise 1.000000 temb_t 0.999990 hidden_after_proj_in 0.999986 enc_after_cond_emb 0.999791 layer0_sa_output 0.999911 hidden_after_layer0 0.999958 hidden_after_layer6 0.999829 hidden_after_layer12 0.999444 hidden_after_layer18 0.998705 hidden_after_layer23 0.998956 dit_step0_vt 0.998899 dit_step0_xt 1.000000 dit_step5_vt 0.999464 dit_step5_xt 0.999980 dit_step10_vt 0.999081 dit_step10_xt 0.999934 dit_step15_vt 0.998074 dit_step15_xt 0.999840 dit_step20_vt 0.995430 dit_step20_xt 0.999586 dit_step25_vt 0.991297 dit_step25_xt 0.999024 dit_step30_vt 0.986693 dit_step30_xt 0.997969 dit_step35_vt 0.981936 dit_step35_xt 0.996519 dit_step40_vt 0.979008 dit_step40_xt 0.994983 dit_step45_vt 0.982747 dit_step45_xt 0.993857 dit_step49_vt 0.988608 dit_x0 0.993466 vae_audio 0.965213 vae_audio (STFT cosine) 0.985692 [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 0.019781 0.001462 -0.001653 0.978470 -0.001619 0.978872 dit_step5_xt 0.999980 0.076343 0.004361 -0.008355 0.884882 -0.008480 0.883811 dit_step10_xt 0.999934 0.123622 0.006953 -0.015055 0.801047 -0.015075 0.802324 dit_step15_xt 0.999840 0.168954 0.009869 -0.021725 0.730609 -0.021933 0.731304 dit_step20_xt 0.999586 0.229020 0.014558 -0.028448 0.677822 -0.028882 0.679066 dit_step25_xt 0.999024 0.435407 0.020817 -0.035260 0.647194 -0.035643 0.650780 dit_step30_xt 0.997969 0.670508 0.029064 -0.042113 0.641976 -0.042577 0.647107 dit_step35_xt 0.996519 0.891543 0.038816 -0.048973 0.662867 -0.049471 0.669256 dit_step40_xt 0.994983 1.132401 0.049644 -0.055862 0.707535 -0.056532 0.715783 dit_step45_xt 0.993857 1.346271 0.059859 -0.062854 0.771631 -0.063533 0.780575 [Xl-turbo] steps=8, shift=3.0 | acestep-v15-xl-turbo-Q8_0.gguf [GGML] Running acestep-v15-xl-turbo-Q8_0.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 08:35:04.810 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 08:35:04.810 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 08:35:04.811 | 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 08:35:04.813 | INFO | acestep.core.generation.handler.generate_music:_vram_preflight_check:156 - [generate_music] VRAM pre-flight: 77.36 GB free, ~1.23 GB needed (batch=1, duration=88s, mode=xl_turbo). 2026-07-12 08:35:04.819 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 08:35:04.823 | 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 08:35:04.824 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 08:35:04.824 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 08:35:04.824 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 08:35:04.824 | 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 08:35:04.824 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 08:35:04.824 | 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 08:35:04.824 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 08:35:04.828 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 08:35:04.836 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 08:35:04.836 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 08:35:04.843 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)... 2026-07-12 08:35:04.850 | 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 08:35:05.394 | INFO | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:42 - [generate_music] Model generation completed. Decoding latents... 2026-07-12 08:35:05.395 | 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 08:35:05.395 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:65 - [generate_music] time_costs: {'encoder_time_cost': 0.00640416145324707, 'diffusion_time_cost': 0.5439348220825195, 'diffusion_per_step_time_cost': 0.06799185276031494, 'total_time_cost': 0.5503389835357666, 'offload_time_cost': 0.0} 2026-07-12 08:35:05.418 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:127 - [generate_music] Decoding latents with VAE... 2026-07-12 08:35:05.420 | DEBUG | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:136 - [generate_music] Before VAE decode: allocated=17.04GB, max=18.34GB 2026-07-12 08:35:05.420 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:154 - [generate_music] Effective free VRAM before VAE decode: 77.27 GB 2026-07-12 08:35:05.420 | 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 08:35:05.420 | DEBUG | acestep.core.generation.handler.memory_utils:_get_auto_decode_chunk_size:108 - [_get_auto_decode_chunk_size] Effective free VRAM: 77.27 GB 2026-07-12 08:35:05.420 | DEBUG | acestep.core.generation.handler.memory_utils:_should_offload_wav_to_cpu:131 - [_should_offload_wav_to_cpu] Effective free VRAM: 77.27 GB 2026-07-12 08:35:05.420 | 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 08:35:05.695 | 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 08:35:05.895 | 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 08:35:05.899 | 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-Q8_0.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-Q8_0.gguf: 830 tensors, data at offset 69056 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-sft-Q8_0.gguf: 830 tensors, data at offset 69056 [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: 258 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-Q8_0.gguf: 830 tensors, data at offset 69056 [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, 616.6 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L, CLS), text_proj, null_cond [Store] Load CondEnc: 347 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, 135.8 ms [Debug] enc_hidden: [238, 2048] first4: 0.686937 -0.019156 -0.051555 0.022736 [Store] Unload CondEnc (616.6 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-Q8_0.gguf: 830 tensors, data at offset 69056 [WeightCtx] Loaded 30 tensors, 106.5 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 76 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 501.6 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.126218 1.441045 0.305219 -0.629688 [Store] Unload FSQ-Detok (106.5 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: -0.126218 1.441045 0.305219 -0.629688 [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-Q8_0.gguf: 830 tensors, data at offset 69056 [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, 4230.2 MB into backend [Load] DiT: 32 layers, H=2560, Nh=32/8, D=128 [Store] Load DiT: 2794 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: 0.012917 0.105451 0.074363 -0.032316 [Debug] temb: [2560] first4: 0.009484 -0.007646 -0.006176 0.004539 [Debug] temb_t: [2560] first4: 0.007823 -0.007880 -0.006709 0.003563 [Debug] temb_r: [2560] first4: 0.001661 0.000234 0.000533 0.000975 [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: 0.033000 -0.082023 0.089453 -0.064865 [Debug] temb_lin1_r: [2560] first4: 0.006798 -0.005077 -0.002197 -0.011157 [Debug] hidden_after_proj_in: [2560, 1085] first4: 0.332896 -0.494266 0.100738 -0.212418 [Debug] proj_in_input: [192, 2170] first4: -0.126218 1.441045 0.305219 -0.629688 [Debug] enc_after_cond_emb: [2560, 238] first4: 0.035997 0.642421 0.117086 0.870434 [Debug] layer0_sa_input: [2560, 1085] first4: 0.037157 -0.019220 0.099356 -0.097384 [Debug] layer0_q_after_rope: [128, 32] first4: -0.275659 -2.152586 0.308523 -0.009736 [Debug] layer0_k_after_rope: [128, 8] first4: 0.698652 2.944157 1.163719 2.030455 [Debug] layer0_sa_output: [2560, 1085] first4: 1.889837 4.370225 -0.862801 7.825058 [Debug] layer0_attn_out: [4096, 1085] first4: 0.457090 -2.168639 -0.540006 -4.110604 [Debug] layer0_after_self_attn: [2560, 1085] first4: 0.457090 -2.168639 -0.540006 -4.110604 [Debug] layer0_after_cross_attn: [2560, 1085] first4: 0.293262 -1.898011 -0.457177 -4.191905 [Debug] hidden_after_layer0: [2560, 1085] first4: -1.706833 -1.232268 247.762390 -3.927608 [Debug] hidden_after_layer6: [2560, 1085] first4: -7.879635 3.664357 315.311981 -21.930168 [Debug] hidden_after_layer12: [2560, 1085] first4: -24.024397 39.492359 230.458252 16.594635 [Debug] hidden_after_layer18: [2560, 1085] first4: 9.399558 -13.303671 233.932190 19.979710 [Debug] hidden_after_layer31: [2560, 1085] first4: 62.853333 -105.289902 7.430450 86.143692 [Debug] dit_step0_vt: [2170, 64] first4: -0.326653 2.216254 0.017260 1.696667 [Debug] dit_step0_xt: [2170, 64] first4: 0.200869 2.111925 -0.172220 0.813723 [DiT] Step 1/50 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.347023 2.151271 0.061904 1.556024 [Debug] dit_step1_xt: [2170, 64] first4: 0.207809 2.068899 -0.173458 0.782602 [DiT] Step 2/50 t=0.980 [Debug] dit_step2_vt: [2170, 64] first4: -0.330435 2.183665 0.054770 1.568143 [Debug] dit_step2_xt: [2170, 64] first4: 0.214418 2.025226 -0.174554 0.751240 [DiT] Step 3/50 t=0.960 [Debug] dit_step3_vt: [2170, 64] first4: -0.274530 2.135809 0.030121 1.567795 [Debug] dit_step3_xt: [2170, 64] first4: 0.219909 1.982510 -0.175156 0.719884 [DiT] Step 4/50 t=0.940 [Debug] dit_step4_vt: [2170, 64] first4: -0.272521 2.060905 0.006454 1.587581 [Debug] dit_step4_xt: [2170, 64] first4: 0.225359 1.941292 -0.175285 0.688132 [DiT] Step 5/50 t=0.920 [Debug] dit_step5_vt: [2170, 64] first4: -0.261852 2.050493 0.022917 1.584365 [Debug] dit_step5_xt: [2170, 64] first4: 0.230596 1.900282 -0.175744 0.656445 [DiT] Step 6/50 t=0.900 [Debug] dit_step6_vt: [2170, 64] first4: -0.251094 2.020633 0.061996 1.602693 [Debug] dit_step6_xt: [2170, 64] first4: 0.235618 1.859869 -0.176983 0.624391 [DiT] Step 7/50 t=0.880 [Debug] dit_step7_vt: [2170, 64] first4: -0.247443 1.998817 0.103574 1.606087 [Debug] dit_step7_xt: [2170, 64] first4: 0.240567 1.819893 -0.179055 0.592269 [DiT] Step 8/50 t=0.860 [Debug] dit_step8_vt: [2170, 64] first4: -0.251424 1.933453 0.133201 1.605178 [Debug] dit_step8_xt: [2170, 64] first4: 0.245595 1.781224 -0.181719 0.560166 [DiT] Step 9/50 t=0.840 [Debug] dit_step9_vt: [2170, 64] first4: -0.280988 1.882344 0.130977 1.603161 [Debug] dit_step9_xt: [2170, 64] first4: 0.251215 1.743577 -0.184338 0.528102 [DiT] Step 10/50 t=0.820 [Debug] dit_step10_vt: [2170, 64] first4: -0.300581 1.830106 0.123942 1.598101 [Debug] dit_step10_xt: [2170, 64] first4: 0.257227 1.706975 -0.186817 0.496140 [DiT] Step 11/50 t=0.800 [Debug] dit_step11_vt: [2170, 64] first4: -0.292664 1.783884 0.102483 1.580303 [Debug] dit_step11_xt: [2170, 64] first4: 0.263080 1.671297 -0.188867 0.464534 [DiT] Step 12/50 t=0.780 [Debug] dit_step12_vt: [2170, 64] first4: -0.294583 1.739592 0.087879 1.565111 [Debug] dit_step12_xt: [2170, 64] first4: 0.268972 1.636505 -0.190625 0.433232 [DiT] Step 13/50 t=0.760 [Debug] dit_step13_vt: [2170, 64] first4: -0.290001 1.687358 0.083082 1.554364 [Debug] dit_step13_xt: [2170, 64] first4: 0.274772 1.602758 -0.192286 0.402145 [DiT] Step 14/50 t=0.740 [Debug] dit_step14_vt: [2170, 64] first4: -0.274726 1.629813 0.052616 1.560603 [Debug] dit_step14_xt: [2170, 64] first4: 0.280266 1.570162 -0.193339 0.370933 [DiT] Step 15/50 t=0.720 [Debug] dit_step15_vt: [2170, 64] first4: -0.260906 1.580422 0.035831 1.551068 [Debug] dit_step15_xt: [2170, 64] first4: 0.285484 1.538553 -0.194055 0.339911 [DiT] Step 16/50 t=0.700 [Debug] dit_step16_vt: [2170, 64] first4: -0.259168 1.523745 0.008526 1.549654 [Debug] dit_step16_xt: [2170, 64] first4: 0.290668 1.508079 -0.194226 0.308918 [DiT] Step 17/50 t=0.680 [Debug] dit_step17_vt: [2170, 64] first4: -0.218798 1.485580 0.000242 1.544287 [Debug] dit_step17_xt: [2170, 64] first4: 0.295044 1.478367 -0.194230 0.278033 [DiT] Step 18/50 t=0.660 [Debug] dit_step18_vt: [2170, 64] first4: -0.183320 1.428797 -0.018911 1.538380 [Debug] dit_step18_xt: [2170, 64] first4: 0.298710 1.449791 -0.193852 0.247265 [DiT] Step 19/50 t=0.640 [Debug] dit_step19_vt: [2170, 64] first4: -0.158091 1.392270 -0.026267 1.535519 [Debug] dit_step19_xt: [2170, 64] first4: 0.301872 1.421946 -0.193327 0.216555 [DiT] Step 20/50 t=0.620 [Debug] dit_step20_vt: [2170, 64] first4: -0.136953 1.339066 -0.032384 1.512678 [Debug] dit_step20_xt: [2170, 64] first4: 0.304611 1.395164 -0.192679 0.186301 [DiT] Step 21/50 t=0.600 [Debug] dit_step21_vt: [2170, 64] first4: -0.100942 1.284204 -0.058128 1.507910 [Debug] dit_step21_xt: [2170, 64] first4: 0.306630 1.369480 -0.191517 0.156143 [DiT] Step 22/50 t=0.580 [Debug] dit_step22_vt: [2170, 64] first4: -0.079450 1.235447 -0.075570 1.489184 [Debug] dit_step22_xt: [2170, 64] first4: 0.308219 1.344771 -0.190005 0.126359 [DiT] Step 23/50 t=0.560 [Debug] dit_step23_vt: [2170, 64] first4: -0.069273 1.173941 -0.084406 1.477288 [Debug] dit_step23_xt: [2170, 64] first4: 0.309604 1.321293 -0.188317 0.096813 [DiT] Step 24/50 t=0.540 [Debug] dit_step24_vt: [2170, 64] first4: -0.038689 1.126569 -0.086074 1.455799 [Debug] dit_step24_xt: [2170, 64] first4: 0.310378 1.298761 -0.186596 0.067697 [DiT] Step 25/50 t=0.520 [Debug] dit_step25_vt: [2170, 64] first4: -0.017510 1.071862 -0.074706 1.420318 [Debug] dit_step25_xt: [2170, 64] first4: 0.310728 1.277324 -0.185102 0.039291 [DiT] Step 26/50 t=0.500 [Debug] dit_step26_vt: [2170, 64] first4: -0.040338 1.013913 -0.103133 1.408655 [Debug] dit_step26_xt: [2170, 64] first4: 0.311535 1.257046 -0.183039 0.011118 [DiT] Step 27/50 t=0.480 [Debug] dit_step27_vt: [2170, 64] first4: -0.031397 0.954604 -0.118475 1.383271 [Debug] dit_step27_xt: [2170, 64] first4: 0.312163 1.237953 -0.180669 -0.016547 [DiT] Step 28/50 t=0.460 [Debug] dit_step28_vt: [2170, 64] first4: -0.044549 0.887060 -0.110914 1.354547 [Debug] dit_step28_xt: [2170, 64] first4: 0.313054 1.220212 -0.178451 -0.043638 [DiT] Step 29/50 t=0.440 [Debug] dit_step29_vt: [2170, 64] first4: -0.044062 0.814407 -0.151253 1.348024 [Debug] dit_step29_xt: [2170, 64] first4: 0.313935 1.203924 -0.175426 -0.070599 [DiT] Step 30/50 t=0.420 [Debug] dit_step30_vt: [2170, 64] first4: -0.066446 0.722144 -0.183047 1.311494 [Debug] dit_step30_xt: [2170, 64] first4: 0.315264 1.189481 -0.171765 -0.096829 [DiT] Step 31/50 t=0.400 [Debug] dit_step31_vt: [2170, 64] first4: -0.064727 0.665684 -0.198274 1.288997 [Debug] dit_step31_xt: [2170, 64] first4: 0.316559 1.176168 -0.167800 -0.122609 [DiT] Step 32/50 t=0.380 [Debug] dit_step32_vt: [2170, 64] first4: -0.072850 0.574991 -0.189969 1.258735 [Debug] dit_step32_xt: [2170, 64] first4: 0.318016 1.164668 -0.164000 -0.147783 [DiT] Step 33/50 t=0.360 [Debug] dit_step33_vt: [2170, 64] first4: -0.105249 0.486917 -0.193060 1.249654 [Debug] dit_step33_xt: [2170, 64] first4: 0.320121 1.154929 -0.160139 -0.172776 [DiT] Step 34/50 t=0.340 [Debug] dit_step34_vt: [2170, 64] first4: -0.126677 0.385753 -0.211442 1.210331 [Debug] dit_step34_xt: [2170, 64] first4: 0.322654 1.147214 -0.155910 -0.196983 [DiT] Step 35/50 t=0.320 [Debug] dit_step35_vt: [2170, 64] first4: -0.157926 0.280273 -0.194494 1.173535 [Debug] dit_step35_xt: [2170, 64] first4: 0.325813 1.141609 -0.152020 -0.220454 [DiT] Step 36/50 t=0.300 [Debug] dit_step36_vt: [2170, 64] first4: -0.156465 0.195171 -0.218124 1.139475 [Debug] dit_step36_xt: [2170, 64] first4: 0.328942 1.137706 -0.147658 -0.243243 [DiT] Step 37/50 t=0.280 [Debug] dit_step37_vt: [2170, 64] first4: -0.146613 0.094869 -0.193403 1.100886 [Debug] dit_step37_xt: [2170, 64] first4: 0.331874 1.135808 -0.143790 -0.265261 [DiT] Step 38/50 t=0.260 [Debug] dit_step38_vt: [2170, 64] first4: -0.167546 -0.009862 -0.161347 1.062690 [Debug] dit_step38_xt: [2170, 64] first4: 0.335225 1.136006 -0.140563 -0.286515 [DiT] Step 39/50 t=0.240 [Debug] dit_step39_vt: [2170, 64] first4: -0.190695 -0.129433 -0.161219 1.023659 [Debug] dit_step39_xt: [2170, 64] first4: 0.339039 1.138594 -0.137339 -0.306988 [DiT] Step 40/50 t=0.220 [Debug] dit_step40_vt: [2170, 64] first4: -0.199101 -0.233214 -0.191463 0.982530 [Debug] dit_step40_xt: [2170, 64] first4: 0.343021 1.143258 -0.133509 -0.326639 [DiT] Step 41/50 t=0.200 [Debug] dit_step41_vt: [2170, 64] first4: -0.232984 -0.315967 -0.157942 0.952145 [Debug] dit_step41_xt: [2170, 64] first4: 0.347681 1.149578 -0.130350 -0.345681 [DiT] Step 42/50 t=0.180 [Debug] dit_step42_vt: [2170, 64] first4: -0.264139 -0.417170 -0.085804 0.906952 [Debug] dit_step42_xt: [2170, 64] first4: 0.352964 1.157921 -0.128634 -0.363821 [DiT] Step 43/50 t=0.160 [Debug] dit_step43_vt: [2170, 64] first4: -0.315474 -0.503124 -0.068787 0.867566 [Debug] dit_step43_xt: [2170, 64] first4: 0.359273 1.167984 -0.127259 -0.381172 [DiT] Step 44/50 t=0.140 [Debug] dit_step44_vt: [2170, 64] first4: -0.322435 -0.588898 -0.015308 0.827629 [Debug] dit_step44_xt: [2170, 64] first4: 0.365722 1.179762 -0.126952 -0.397724 [DiT] Step 45/50 t=0.120 [Debug] dit_step45_vt: [2170, 64] first4: -0.356486 -0.679513 0.035510 0.757001 [Debug] dit_step45_xt: [2170, 64] first4: 0.372851 1.193352 -0.127663 -0.412864 [DiT] Step 46/50 t=0.100 [Debug] dit_step46_vt: [2170, 64] first4: -0.390991 -0.745911 0.107527 0.713722 [Debug] dit_step46_xt: [2170, 64] first4: 0.380671 1.208270 -0.129813 -0.427139 [DiT] Step 47/50 t=0.080 [Debug] dit_step47_vt: [2170, 64] first4: -0.449844 -0.834630 0.144434 0.653209 [Debug] dit_step47_xt: [2170, 64] first4: 0.389668 1.224963 -0.132702 -0.440203 [DiT] Step 48/50 t=0.060 [Debug] dit_step48_vt: [2170, 64] first4: -0.499686 -0.879013 0.232432 0.671797 [Debug] dit_step48_xt: [2170, 64] first4: 0.399662 1.242543 -0.137351 -0.453639 [DiT] Step 49/50 t=0.040 [Debug] dit_step49_vt: [2170, 64] first4: -0.499657 -0.865082 0.151631 0.684783 [Debug] dit_x0: [2170, 64] first4: 0.409655 1.259845 -0.140383 -0.467335 [DiT] Step 50/50 t=0.020 [DiT-Generate] Total: 512031.1 ms (512031.1 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.409655 1.259845 -0.140383 -0.467335 [Store] Unload DiT (4230.2 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: 737 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: 27620.8 ms [Debug] vae_audio: [2, 4166400] first4: -0.001387 -0.000674 -0.000790 -0.000307 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 463 ms (187.43x realtime), 32 threads [MP3] Wrote ggml-xl-sft/request00.mp3 [Ace-Synth] All done 2026-07-12 08:44:12.132 | 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 0.999541 detok_output 0.999983 context 0.999990 noise 1.000000 temb_t 0.999994 hidden_after_proj_in 0.999977 enc_after_cond_emb 0.999637 layer0_sa_output 0.999594 hidden_after_layer0 0.999411 hidden_after_layer6 0.999788 hidden_after_layer12 0.997013 hidden_after_layer18 0.996167 hidden_after_layer31 0.988196 dit_step0_vt 0.911490 dit_step0_xt 0.999840 dit_step1_vt 0.927729 dit_step1_xt 0.999525 dit_step2_vt 0.929449 dit_step2_xt 0.998752 dit_step3_vt 0.926179 dit_step3_xt 0.996950 dit_step4_vt 0.920338 dit_step4_xt 0.992455 dit_step5_vt 0.911758 dit_step5_xt 0.981634 dit_step6_vt 0.903335 dit_step6_xt 0.960147 dit_step7_vt 0.882411 dit_x0 0.924992 vae_audio 0.731335 vae_audio (STFT cosine) 0.922430 [Xl-turbo] Error growth GGML vs Python stage cos max_err mean_err mean_A std_A mean_B std_B dit_step0_xt 0.999840 0.159046 0.012522 -0.003005 0.978374 -0.002721 0.976534 dit_step1_xt 0.999525 0.346585 0.021343 -0.005991 0.952131 -0.005567 0.949004 dit_step2_xt 0.998752 0.545028 0.033092 -0.009747 0.923372 -0.009330 0.918931 dit_step3_xt 0.996950 0.810410 0.049114 -0.015408 0.892270 -0.014418 0.887241 dit_step4_xt 0.992455 1.180011 0.074005 -0.023290 0.862897 -0.021453 0.857796 dit_step5_xt 0.981634 1.771124 0.113042 -0.034861 0.846295 -0.032240 0.840033 dit_step6_xt 0.960147 2.524881 0.172073 -0.051853 0.869995 -0.049194 0.863964 [Xl-sft] steps=50, shift=1.0 | acestep-v15-xl-sft-Q8_0.gguf [GGML] Running acestep-v15-xl-sft-Q8_0.gguf... [GGML] Done, 131 dump files [Python] Initializing acestep-v15-xl-sft... Loading checkpoint shards: 0%| | 0/4 [00:00 2026-07-12 08:44:15.481 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 08:44:15.481 | 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 08:44:15.481 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 08:44:15.484 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 08:44:15.492 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 08:44:15.492 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 08:44:15.499 | 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