[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-Q5_K_M.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-Q5_K_M.gguf: 678 tensors, data at offset 56864 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-turbo-Q5_K_M.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: 227 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-Q5_K_M.gguf: 678 tensors, data at offset 56864 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K fused, V separate [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K fused, V separate [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 140 tensors, 412.5 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L), text_proj, null_cond [Store] Load CondEnc: 688 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, 121.0 ms [Debug] enc_hidden: [238, 2048] first4: 1.761670 -0.053200 -0.132888 0.058852 [Store] Unload CondEnc (412.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] Detokenizer backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-turbo-Q5_K_M.gguf: 678 tensors, data at offset 56864 [WeightCtx] Loaded 30 tensors, 73.2 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 61 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 419.4 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.129311 1.458194 0.298132 -0.651512 [Store] Unload FSQ-Detok (73.2 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: -0.129311 1.458194 0.298132 -0.651512 [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-Q5_K_M.gguf: 678 tensors, data at offset 56864 [DiT] Self-attn: Q+K fused, V separate [DiT] Cross-attn: all separate [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 478 tensors, 1061.2 MB into backend [Load] DiT: 24 layers, H=2048, Nh=16/8, D=128 [Store] Load DiT: 764 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2063 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [12288] first4: 0.261152 -0.161305 -0.103153 0.050892 [Debug] temb: [2048] first4: -0.000119 -0.132132 -0.035650 0.065085 [Debug] temb_t: [2048] first4: 0.000588 0.026848 -0.052924 0.063878 [Debug] temb_r: [2048] first4: -0.000708 -0.158980 0.017274 0.001208 [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: -0.051319 -0.053246 -0.011899 -0.038818 [Debug] temb_lin1_r: [2048] first4: -0.016165 -0.021121 -0.015801 -0.000525 [Debug] hidden_after_proj_in: [2048, 1085] first4: -1.048950 -0.942691 0.537616 0.450821 [Debug] proj_in_input: [192, 2170] first4: -0.129311 1.458194 0.298132 -0.651512 [Debug] enc_after_cond_emb: [2048, 238] first4: -0.145323 0.751763 0.348497 -0.533064 [Debug] layer0_sa_input: [2048, 1085] first4: -0.726623 -0.748099 -0.053174 0.262053 [Debug] layer0_q_after_rope: [128, 16] first4: -0.145323 0.751763 0.348497 -0.533064 [Debug] layer0_k_after_rope: [128, 8] first4: -1.551454 -1.000395 0.163224 0.462218 [Debug] layer0_sa_output: [2048, 1085] first4: -1.509493 0.130514 -0.385214 0.484345 [Debug] layer0_attn_out: [2048, 1085] first4: -1.551454 -1.000395 0.163224 0.462218 [Debug] layer0_after_self_attn: [2048, 1085] first4: -1.551454 -1.000395 0.163224 0.462218 [Debug] layer0_after_cross_attn: [2048, 1085] first4: -1.602293 -0.775263 -0.326485 0.501063 [Debug] hidden_after_layer0: [2048, 1085] first4: -9.293168 0.737673 51.618420 -0.869608 [Debug] hidden_after_layer6: [2048, 1085] first4: -20.846735 0.989748 29.713915 -4.707834 [Debug] hidden_after_layer12: [2048, 1085] first4: -18.078571 -17.109922 66.804359 24.826223 [Debug] hidden_after_layer18: [2048, 1085] first4: -26.631359 11.560244 58.145016 19.027023 [Debug] hidden_after_layer23: [2048, 1085] first4: -3.675964 36.309525 197.822388 157.329468 [Debug] dit_step0_vt: [2170, 64] first4: -0.002206 1.127751 0.286357 2.379969 [Debug] dit_step0_xt: [2170, 64] first4: 0.194436 2.104989 -0.184891 0.739476 [DiT] Step 1/8 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.249564 1.364493 -0.159354 1.897966 [Debug] dit_step1_xt: [2170, 64] first4: 0.208049 2.030562 -0.176199 0.635950 [DiT] Step 2/8 t=0.955 [Debug] dit_step2_vt: [2170, 64] first4: -0.075789 1.247166 0.092347 2.368074 [Debug] dit_step2_xt: [2170, 64] first4: 0.213101 1.947417 -0.182356 0.478079 [DiT] Step 3/8 t=0.900 [Debug] dit_step3_vt: [2170, 64] first4: 0.249461 1.105958 0.234605 2.653776 [Debug] dit_step3_xt: [2170, 64] first4: 0.192313 1.855254 -0.201906 0.256931 [DiT] Step 4/8 t=0.833 [Debug] dit_step4_vt: [2170, 64] first4: 0.323155 0.867028 0.076578 2.721846 [Debug] dit_step4_xt: [2170, 64] first4: 0.157689 1.762358 -0.210111 -0.034695 [DiT] Step 5/8 t=0.750 [Debug] dit_step5_vt: [2170, 64] first4: 0.347711 0.761805 -0.411626 2.774529 [Debug] dit_step5_xt: [2170, 64] first4: 0.108016 1.653529 -0.151307 -0.431057 [DiT] Step 6/8 t=0.643 [Debug] dit_step6_vt: [2170, 64] first4: 0.182753 0.680159 -0.950754 2.783073 [Debug] dit_step6_xt: [2170, 64] first4: 0.071466 1.517497 0.038844 -0.987671 [DiT] Step 7/8 t=0.500 [Debug] dit_step7_vt: [2170, 64] first4: -0.012229 0.341252 -1.360142 3.065000 [Debug] dit_x0: [2170, 64] first4: 0.075134 1.415122 0.446886 -1.907171 [DiT] Step 8/8 t=0.300 [DiT-Generate] Total: 27390.5 ms (27390.5 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.075134 1.415122 0.446886 -1.907171 [Store] Unload DiT (1061.2 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: 710 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: 27454.0 ms [Debug] vae_audio: [2, 4166400] first4: 0.000895 0.001621 0.001397 0.001936 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 503 ms (172.48x realtime), 32 threads [MP3] Wrote ggml-turbo/request00.mp3 [Ace-Synth] All done 2026-07-12 08:57:53.370 | 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 08:57:55.008 | WARNING | acestep.training.trainer::40 - bitsandbytes not installed. Using standard AdamW. 2026-07-12 08:57:55.010 | 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 08:57:55.088 | 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 08:57:56.468 | 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 08:57:56.468 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 08:57:56.468 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 08:57:56.469 | 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 08:57:56.472 | INFO | acestep.core.generation.handler.generate_music:_vram_preflight_check:156 - [generate_music] VRAM pre-flight: 87.83 GB free, ~0.94 GB needed (batch=1, duration=88s, mode=turbo). 2026-07-12 08:57:56.478 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 08:57:56.673 | 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 08:57:56.675 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 08:57:56.675 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 08:57:56.675 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 08:57:56.675 | 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 08:57:56.675 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 08:57:56.675 | 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 08:57:56.675 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 08:57:56.682 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 08:57:56.697 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 08:57:56.697 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 08:57:56.721 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)... 2026-07-12 08:57:56.728 | 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 08:57:56.813 | 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 08:57:57.037 | INFO | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:42 - [generate_music] Model generation completed. Decoding latents... 2026-07-12 08:57:57.046 | 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 08:57:57.046 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:65 - [generate_music] time_costs: {'encoder_time_cost': 0.0069866180419921875, 'diffusion_time_cost': 0.30900049209594727, 'diffusion_per_step_time_cost': 0.03862506151199341, 'total_time_cost': 0.31598711013793945, 'offload_time_cost': 0.0} 2026-07-12 08:57:57.052 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:127 - [generate_music] Decoding latents with VAE... 2026-07-12 08:57:57.054 | 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 08:57:57.054 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:154 - [generate_music] Effective free VRAM before VAE decode: 87.72 GB 2026-07-12 08:57:57.054 | 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 08:57:57.054 | DEBUG | acestep.core.generation.handler.memory_utils:_get_auto_decode_chunk_size:108 - [_get_auto_decode_chunk_size] Effective free VRAM: 87.72 GB 2026-07-12 08:57:57.054 | DEBUG | acestep.core.generation.handler.memory_utils:_should_offload_wav_to_cpu:131 - [_should_offload_wav_to_cpu] Effective free VRAM: 87.72 GB 2026-07-12 08:57:57.054 | 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 08:57:57.330 | 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 08:57:57.491 | 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 08:57:57.494 | 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-Q5_K_M.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-Q5_K_M.gguf: 678 tensors, data at offset 56800 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-sft-Q5_K_M.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: 219 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-Q5_K_M.gguf: 678 tensors, data at offset 56800 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K fused, V separate [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K fused, V separate [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 140 tensors, 412.5 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L), text_proj, null_cond [Store] Load CondEnc: 685 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, 124.6 ms [Debug] enc_hidden: [238, 2048] first4: 1.761670 -0.053200 -0.132888 0.058852 [Store] Unload CondEnc (412.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] Detokenizer backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-sft-Q5_K_M.gguf: 678 tensors, data at offset 56800 [WeightCtx] Loaded 30 tensors, 73.2 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 60 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 417.3 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.129311 1.458194 0.298132 -0.651512 [Store] Unload FSQ-Detok (73.2 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: -0.129311 1.458194 0.298132 -0.651512 [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-Q5_K_M.gguf: 678 tensors, data at offset 56800 [DiT] Self-attn: Q+K fused, V separate [DiT] Cross-attn: all separate [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 478 tensors, 1061.2 MB into backend [Load] DiT: 24 layers, H=2048, Nh=16/8, D=128 [Store] Load DiT: 768 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2063 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [12288] first4: 0.155936 -0.117620 -0.084492 0.081893 [Debug] temb: [2048] first4: -0.002754 -0.176678 0.004687 -0.001972 [Debug] temb_t: [2048] first4: -0.001256 0.003101 -0.012669 -0.001763 [Debug] temb_r: [2048] first4: -0.001498 -0.179779 0.017356 -0.000209 [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: -0.034934 0.029198 0.027409 -0.031502 [Debug] temb_lin1_r: [2048] first4: -0.002680 0.004202 0.000655 -0.002088 [Debug] hidden_after_proj_in: [2048, 1085] first4: -1.099326 -0.899651 0.499825 0.444552 [Debug] proj_in_input: [192, 2170] first4: -0.129311 1.458194 0.298132 -0.651512 [Debug] enc_after_cond_emb: [2048, 238] first4: -0.166779 0.841212 0.381438 -0.573819 [Debug] layer0_sa_input: [2048, 1085] first4: -0.922690 -0.700908 -0.034981 0.295921 [Debug] layer0_q_after_rope: [128, 16] first4: -0.166779 0.841212 0.381438 -0.573819 [Debug] layer0_k_after_rope: [128, 8] first4: -1.796069 -1.336702 -0.152231 0.385512 [Debug] layer0_sa_output: [2048, 1085] first4: -1.616210 0.770564 -0.580455 0.537726 [Debug] layer0_attn_out: [2048, 1085] first4: -1.796069 -1.336702 -0.152231 0.385512 [Debug] layer0_after_self_attn: [2048, 1085] first4: -1.796069 -1.336702 -0.152231 0.385512 [Debug] layer0_after_cross_attn: [2048, 1085] first4: -1.972029 -1.019393 -0.413236 0.394381 [Debug] hidden_after_layer0: [2048, 1085] first4: -9.690948 1.413015 60.449055 -1.652728 [Debug] hidden_after_layer6: [2048, 1085] first4: -16.032001 2.777304 60.309673 -1.417665 [Debug] hidden_after_layer12: [2048, 1085] first4: -13.579681 2.601818 -15.388254 -0.629633 [Debug] hidden_after_layer18: [2048, 1085] first4: -6.477047 16.179531 -40.314045 -11.229168 [Debug] hidden_after_layer23: [2048, 1085] first4: 35.650501 64.484314 52.944641 -18.251856 [Debug] dit_step0_vt: [2170, 64] first4: -0.657627 2.496069 -0.170021 1.409376 [Debug] dit_step0_xt: [2170, 64] first4: 0.207488 2.106329 -0.168475 0.819469 [DiT] Step 1/50 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.714396 2.509334 -0.058743 1.236221 [Debug] dit_step1_xt: [2170, 64] first4: 0.221776 2.056142 -0.167300 0.794744 [DiT] Step 2/50 t=0.980 [Debug] dit_step2_vt: [2170, 64] first4: -0.697460 2.508775 0.034986 1.306383 [Debug] dit_step2_xt: [2170, 64] first4: 0.235726 2.005966 -0.167999 0.768617 [DiT] Step 3/50 t=0.960 [Debug] dit_step3_vt: [2170, 64] first4: -0.697118 2.415090 0.037855 1.297944 [Debug] dit_step3_xt: [2170, 64] first4: 0.249668 1.957665 -0.168757 0.742658 [DiT] Step 4/50 t=0.940 [Debug] dit_step4_vt: [2170, 64] first4: -0.602095 2.320011 -0.002184 1.288608 [Debug] dit_step4_xt: [2170, 64] first4: 0.261710 1.911264 -0.168713 0.716886 [DiT] Step 5/50 t=0.920 [Debug] dit_step5_vt: [2170, 64] first4: -0.589762 2.295776 0.016944 1.278431 [Debug] dit_step5_xt: [2170, 64] first4: 0.273505 1.865349 -0.169052 0.691317 [DiT] Step 6/50 t=0.900 [Debug] dit_step6_vt: [2170, 64] first4: -0.574608 2.234402 0.000571 1.288834 [Debug] dit_step6_xt: [2170, 64] first4: 0.284997 1.820661 -0.169063 0.665540 [DiT] Step 7/50 t=0.880 [Debug] dit_step7_vt: [2170, 64] first4: -0.533204 2.178506 -0.056891 1.280819 [Debug] dit_step7_xt: [2170, 64] first4: 0.295661 1.777091 -0.167925 0.639924 [DiT] Step 8/50 t=0.860 [Debug] dit_step8_vt: [2170, 64] first4: -0.455220 2.094212 -0.047918 1.294091 [Debug] dit_step8_xt: [2170, 64] first4: 0.304766 1.735207 -0.166967 0.614042 [DiT] Step 9/50 t=0.840 [Debug] dit_step9_vt: [2170, 64] first4: -0.381123 1.974700 -0.038506 1.269894 [Debug] dit_step9_xt: [2170, 64] first4: 0.312388 1.695713 -0.166197 0.588644 [DiT] Step 10/50 t=0.820 [Debug] dit_step10_vt: [2170, 64] first4: -0.354808 1.865164 -0.019080 1.252590 [Debug] dit_step10_xt: [2170, 64] first4: 0.319484 1.658409 -0.165815 0.563592 [DiT] Step 11/50 t=0.800 [Debug] dit_step11_vt: [2170, 64] first4: -0.327874 1.788247 -0.006149 1.241280 [Debug] dit_step11_xt: [2170, 64] first4: 0.326042 1.622644 -0.165692 0.538767 [DiT] Step 12/50 t=0.780 [Debug] dit_step12_vt: [2170, 64] first4: -0.280075 1.745975 0.036432 1.214846 [Debug] dit_step12_xt: [2170, 64] first4: 0.331643 1.587725 -0.166421 0.514470 [DiT] Step 13/50 t=0.760 [Debug] dit_step13_vt: [2170, 64] first4: -0.267799 1.661762 -0.046870 1.208841 [Debug] dit_step13_xt: [2170, 64] first4: 0.336999 1.554490 -0.165484 0.490293 [DiT] Step 14/50 t=0.740 [Debug] dit_step14_vt: [2170, 64] first4: -0.285340 1.576343 -0.052269 1.167546 [Debug] dit_step14_xt: [2170, 64] first4: 0.342706 1.522963 -0.164438 0.466942 [DiT] Step 15/50 t=0.720 [Debug] dit_step15_vt: [2170, 64] first4: -0.266264 1.489226 -0.021447 1.177500 [Debug] dit_step15_xt: [2170, 64] first4: 0.348031 1.493178 -0.164009 0.443392 [DiT] Step 16/50 t=0.700 [Debug] dit_step16_vt: [2170, 64] first4: -0.263499 1.440395 -0.065862 1.151960 [Debug] dit_step16_xt: [2170, 64] first4: 0.353301 1.464370 -0.162692 0.420353 [DiT] Step 17/50 t=0.680 [Debug] dit_step17_vt: [2170, 64] first4: -0.245335 1.358222 -0.073017 1.160452 [Debug] dit_step17_xt: [2170, 64] first4: 0.358208 1.437206 -0.161232 0.397144 [DiT] Step 18/50 t=0.660 [Debug] dit_step18_vt: [2170, 64] first4: -0.307771 1.301341 -0.120541 1.118375 [Debug] dit_step18_xt: [2170, 64] first4: 0.364364 1.411179 -0.158821 0.374777 [DiT] Step 19/50 t=0.640 [Debug] dit_step19_vt: [2170, 64] first4: -0.287700 1.171471 -0.155624 1.103791 [Debug] dit_step19_xt: [2170, 64] first4: 0.370118 1.387750 -0.155708 0.352701 [DiT] Step 20/50 t=0.620 [Debug] dit_step20_vt: [2170, 64] first4: -0.344085 1.094058 -0.122426 1.090428 [Debug] dit_step20_xt: [2170, 64] first4: 0.376999 1.365869 -0.153260 0.330892 [DiT] Step 21/50 t=0.600 [Debug] dit_step21_vt: [2170, 64] first4: -0.341039 1.035369 -0.108844 1.083295 [Debug] dit_step21_xt: [2170, 64] first4: 0.383820 1.345161 -0.151083 0.309226 [DiT] Step 22/50 t=0.580 [Debug] dit_step22_vt: [2170, 64] first4: -0.356765 0.923145 -0.139819 1.046227 [Debug] dit_step22_xt: [2170, 64] first4: 0.390955 1.326698 -0.148287 0.288302 [DiT] Step 23/50 t=0.560 [Debug] dit_step23_vt: [2170, 64] first4: -0.362925 0.851544 -0.151446 1.057696 [Debug] dit_step23_xt: [2170, 64] first4: 0.398214 1.309667 -0.145258 0.267148 [DiT] Step 24/50 t=0.540 [Debug] dit_step24_vt: [2170, 64] first4: -0.396254 0.785720 -0.092225 0.977860 [Debug] dit_step24_xt: [2170, 64] first4: 0.406139 1.293953 -0.143413 0.247591 [DiT] Step 25/50 t=0.520 [Debug] dit_step25_vt: [2170, 64] first4: -0.421155 0.682049 -0.132900 0.975354 [Debug] dit_step25_xt: [2170, 64] first4: 0.414562 1.280312 -0.140755 0.228084 [DiT] Step 26/50 t=0.500 [Debug] dit_step26_vt: [2170, 64] first4: -0.466535 0.565290 -0.162769 0.966359 [Debug] dit_step26_xt: [2170, 64] first4: 0.423893 1.269006 -0.137500 0.208756 [DiT] Step 27/50 t=0.480 [Debug] dit_step27_vt: [2170, 64] first4: -0.492932 0.449291 -0.141629 0.897976 [Debug] dit_step27_xt: [2170, 64] first4: 0.433751 1.260020 -0.134667 0.190797 [DiT] Step 28/50 t=0.460 [Debug] dit_step28_vt: [2170, 64] first4: -0.530145 0.321659 -0.139424 0.864297 [Debug] dit_step28_xt: [2170, 64] first4: 0.444354 1.253587 -0.131879 0.173511 [DiT] Step 29/50 t=0.440 [Debug] dit_step29_vt: [2170, 64] first4: -0.577199 0.213206 -0.116707 0.886733 [Debug] dit_step29_xt: [2170, 64] first4: 0.455898 1.249323 -0.129545 0.155776 [DiT] Step 30/50 t=0.420 [Debug] dit_step30_vt: [2170, 64] first4: -0.568082 0.104922 -0.085927 0.876891 [Debug] dit_step30_xt: [2170, 64] first4: 0.467260 1.247225 -0.127826 0.138238 [DiT] Step 31/50 t=0.400 [Debug] dit_step31_vt: [2170, 64] first4: -0.516599 0.011507 -0.109571 0.893800 [Debug] dit_step31_xt: [2170, 64] first4: 0.477592 1.246995 -0.125635 0.120362 [DiT] Step 32/50 t=0.380 [Debug] dit_step32_vt: [2170, 64] first4: -0.624011 -0.087004 -0.075667 0.837947 [Debug] dit_step32_xt: [2170, 64] first4: 0.490072 1.248735 -0.124121 0.103603 [DiT] Step 33/50 t=0.360 [Debug] dit_step33_vt: [2170, 64] first4: -0.577008 -0.223618 -0.035624 0.792799 [Debug] dit_step33_xt: [2170, 64] first4: 0.501612 1.253207 -0.123409 0.087748 [DiT] Step 34/50 t=0.340 [Debug] dit_step34_vt: [2170, 64] first4: -0.596153 -0.302784 -0.072460 0.762773 [Debug] dit_step34_xt: [2170, 64] first4: 0.513535 1.259263 -0.121960 0.072492 [DiT] Step 35/50 t=0.320 [Debug] dit_step35_vt: [2170, 64] first4: -0.596805 -0.429495 0.006033 0.770849 [Debug] dit_step35_xt: [2170, 64] first4: 0.525471 1.267853 -0.122080 0.057075 [DiT] Step 36/50 t=0.300 [Debug] dit_step36_vt: [2170, 64] first4: -0.603872 -0.538234 0.025933 0.715570 [Debug] dit_step36_xt: [2170, 64] first4: 0.537549 1.278617 -0.122599 0.042764 [DiT] Step 37/50 t=0.280 [Debug] dit_step37_vt: [2170, 64] first4: -0.566051 -0.578368 0.029349 0.697241 [Debug] dit_step37_xt: [2170, 64] first4: 0.548870 1.290185 -0.123186 0.028819 [DiT] Step 38/50 t=0.260 [Debug] dit_step38_vt: [2170, 64] first4: -0.546682 -0.658521 0.017377 0.649048 [Debug] dit_step38_xt: [2170, 64] first4: 0.559803 1.303355 -0.123533 0.015838 [DiT] Step 39/50 t=0.240 [Debug] dit_step39_vt: [2170, 64] first4: -0.621359 -0.781794 0.069817 0.612406 [Debug] dit_step39_xt: [2170, 64] first4: 0.572231 1.318991 -0.124930 0.003590 [DiT] Step 40/50 t=0.220 [Debug] dit_step40_vt: [2170, 64] first4: -0.591927 -0.838001 0.061115 0.614188 [Debug] dit_step40_xt: [2170, 64] first4: 0.584069 1.335751 -0.126152 -0.008694 [DiT] Step 41/50 t=0.200 [Debug] dit_step41_vt: [2170, 64] first4: -0.569759 -0.929374 0.150862 0.539435 [Debug] dit_step41_xt: [2170, 64] first4: 0.595464 1.354339 -0.129169 -0.019483 [DiT] Step 42/50 t=0.180 [Debug] dit_step42_vt: [2170, 64] first4: -0.547970 -0.995041 0.212866 0.488458 [Debug] dit_step42_xt: [2170, 64] first4: 0.606424 1.374239 -0.133427 -0.029252 [DiT] Step 43/50 t=0.160 [Debug] dit_step43_vt: [2170, 64] first4: -0.504826 -1.099528 0.218499 0.430366 [Debug] dit_step43_xt: [2170, 64] first4: 0.616520 1.396230 -0.137797 -0.037859 [DiT] Step 44/50 t=0.140 [Debug] dit_step44_vt: [2170, 64] first4: -0.547315 -1.128398 0.238149 0.377204 [Debug] dit_step44_xt: [2170, 64] first4: 0.627467 1.418798 -0.142560 -0.045403 [DiT] Step 45/50 t=0.120 [Debug] dit_step45_vt: [2170, 64] first4: -0.491463 -1.150407 0.328831 0.316009 [Debug] dit_step45_xt: [2170, 64] first4: 0.637296 1.441806 -0.149136 -0.051723 [DiT] Step 46/50 t=0.100 [Debug] dit_step46_vt: [2170, 64] first4: -0.456665 -1.209669 0.297244 0.264878 [Debug] dit_step46_xt: [2170, 64] first4: 0.646429 1.466000 -0.155081 -0.057021 [DiT] Step 47/50 t=0.080 [Debug] dit_step47_vt: [2170, 64] first4: -0.479243 -1.301557 0.298145 0.208640 [Debug] dit_step47_xt: [2170, 64] first4: 0.656014 1.492031 -0.161044 -0.061194 [DiT] Step 48/50 t=0.060 [Debug] dit_step48_vt: [2170, 64] first4: -0.390618 -1.297076 0.278085 0.216807 [Debug] dit_step48_xt: [2170, 64] first4: 0.663826 1.517972 -0.166606 -0.065530 [DiT] Step 49/50 t=0.040 [Debug] dit_step49_vt: [2170, 64] first4: -0.425937 -1.293047 0.289450 0.200981 [Debug] dit_x0: [2170, 64] first4: 0.672345 1.543833 -0.172395 -0.069550 [DiT] Step 50/50 t=0.020 [DiT-Generate] Total: 172691.5 ms (172691.5 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.672345 1.543833 -0.172395 -0.069550 [Store] Unload DiT (1061.2 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: 707 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: 27345.5 ms [Debug] vae_audio: [2, 4166400] first4: -0.001453 -0.000926 -0.001202 -0.000798 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 443 ms (195.77x realtime), 32 threads [MP3] Wrote ggml-sft/request00.mp3 [Ace-Synth] All done 2026-07-12 09:01:22.030 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:174 - [initialize_service] Attempting to load model with attention implementation: sdpa 2026-07-12 09:01:23.090 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 09:01:23.091 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 09:01:23.091 | INFO | acestep.core.generation.handler.generate_music_request:_prepare_reference_and_source_audio:179 - [generate_music] cover task: no src_audio but audio codes provided, proceeding with codes 2026-07-12 09:01:23.094 | INFO | acestep.core.generation.handler.generate_music:_vram_preflight_check:156 - [generate_music] VRAM pre-flight: 81.68 GB free, ~0.94 GB needed (batch=1, duration=88s, mode=turbo). 2026-07-12 09:01:23.099 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 09:01:23.104 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_precomputed_lm_hints:31 - [generate_music] Decoding audio codes for LM hints for item 0... 2026-07-12 09:01:23.107 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 09:01:23.107 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 09:01:23.107 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 09:01:23.107 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:122 - text_prompt: # Instruction Generate audio semantic tokens based on the given conditions: # Caption An upbeat and anthemic pop-rock track driven by bright, slightly overdriven # Metas - bpm: 83 - timesignature: 4 - keyscale: G major - duration: 88 seconds <|endoftext|> 2026-07-12 09:01:23.107 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 09:01:23.107 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:124 - lyrics_text: # Languages fr # Lyric # Lyric [Intro - Guitar Riff] [Verse 1] Dans le monde des tutos virtuels G ta toise en nouvelle passion Avec Ggendoline et PumbΓ© Γ  midi La communautΓ©, c'est l'unitΓ© Quel joie, une clΓ© [Chorus] Dans le monde des tutos virtuels GΓ’ndoline et PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner [Guitar Solo] [Verse 2] Dans le monde des tutos virtuels GΓ’ndoline, PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner<|endoftext|> 2026-07-12 09:01:23.107 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 09:01:23.110 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 09:01:23.119 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 09:01:23.119 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 09:01:23.125 | 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-Q5_K_M.gguf [GGML] Running acestep-v15-turbo-Q5_K_M.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 0.999097 detok_output 0.999843 context 0.999900 noise 1.000000 temb_t 0.999968 hidden_after_proj_in 0.999953 enc_after_cond_emb 0.999197 layer0_sa_output 0.999388 hidden_after_layer0 0.999772 hidden_after_layer6 0.999687 hidden_after_layer12 0.998693 hidden_after_layer18 0.995645 hidden_after_layer23 0.991758 dit_step0_vt 0.969782 dit_step0_xt 0.999933 dit_step1_vt 0.972799 dit_step1_xt 0.999792 dit_step2_vt 0.971332 dit_step2_xt 0.999399 dit_step3_vt 0.974239 dit_step3_xt 0.998577 dit_step4_vt 0.972245 dit_step4_xt 0.996707 dit_step5_vt 0.967987 dit_step5_xt 0.992344 dit_step6_vt 0.963553 dit_step6_xt 0.983770 dit_step7_vt 0.954766 dit_x0 0.970780 vae_audio 0.878432 vae_audio (STFT cosine) 0.969365 [Turbo] Error growth GGML vs Python stage cos max_err mean_err mean_A std_A mean_B std_B dit_step0_xt 0.999933 0.138257 0.007678 -0.002290 0.973047 -0.002342 0.972003 dit_step1_xt 0.999792 0.270737 0.013151 -0.005300 0.942881 -0.005313 0.941730 dit_step2_xt 0.999399 0.460268 0.020988 -0.009308 0.909498 -0.009311 0.908527 dit_step3_xt 0.998577 0.689647 0.031134 -0.014715 0.874229 -0.014577 0.873624 dit_step4_xt 0.996707 0.849085 0.045339 -0.021939 0.842458 -0.021660 0.841995 dit_step5_xt 0.992344 1.317355 0.067062 -0.032318 0.825966 -0.032109 0.824593 dit_step6_xt 0.983770 2.173034 0.100468 -0.046952 0.857183 -0.046482 0.855546 [SFT] steps=50, shift=1.0 | acestep-v15-sft-Q5_K_M.gguf [GGML] Running acestep-v15-sft-Q5_K_M.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-Q5_K_M.gguf: 830 tensors, data at offset 69088 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-turbo-Q5_K_M.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: 224 ms [Debug] text_hidden: [70, 1024] first4: 3.704526 2.436253 0.222853 -13.131872 [Debug] lyric_embed: [167, 1024] first4: 0.029175 0.032227 -0.022339 -0.028809 [Store] Unload TextEnc (1136.5 MB) load_backend: loaded CUDA backend from /mnt/workspace/git/acestep.cpp/build/libggml-cuda.so load_backend: loaded Vulkan backend from /mnt/workspace/git/acestep.cpp/build/libggml-vulkan.so load_backend: loaded CPU backend from /mnt/workspace/git/acestep.cpp/build/libggml-cpu-zen4.so [Load] CondEncoder backend: CPU (CPU threads: 16) [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-turbo-Q5_K_M.gguf: 830 tensors, data at offset 69088 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K fused, V separate [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K fused, V separate [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 141 tensors, 416.2 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L, CLS), text_proj, null_cond [Store] Load CondEnc: 714 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, 125.7 ms [Debug] enc_hidden: [238, 2048] first4: 0.688062 -0.020657 -0.051642 0.022549 [Store] Unload CondEnc (416.2 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-Q5_K_M.gguf: 830 tensors, data at offset 69088 [WeightCtx] Loaded 30 tensors, 73.2 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 61 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 422.2 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.129311 1.458194 0.298132 -0.651512 [Store] Unload FSQ-Detok (73.2 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: -0.129311 1.458194 0.298132 -0.651512 [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-Q5_K_M.gguf: 830 tensors, data at offset 69088 [DiT] Self-attn: Q+K fused, V separate [DiT] Cross-attn: all separate [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 630 tensors, 2801.1 MB into backend [Load] DiT: 32 layers, H=2560, Nh=32/8, D=128 [Store] Load DiT: 2018 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2729 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [15360] first4: 0.007412 0.108993 0.074316 -0.076962 [Debug] temb: [2560] first4: 0.026376 -0.023438 -0.016236 0.047262 [Debug] temb_t: [2560] first4: 0.014536 -0.022293 -0.020594 0.048466 [Debug] temb_r: [2560] first4: 0.011840 -0.001145 0.004359 -0.001204 [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: 0.063305 -0.019139 0.138854 -0.115857 [Debug] temb_lin1_r: [2560] first4: -0.008961 0.017832 -0.016914 0.012844 [Debug] hidden_after_proj_in: [2560, 1085] first4: 0.352658 -0.584319 0.235708 -0.182073 [Debug] proj_in_input: [192, 2170] first4: -0.129311 1.458194 0.298132 -0.651512 [Debug] enc_after_cond_emb: [2560, 238] first4: 0.047516 0.666162 0.102776 0.870838 [Debug] layer0_sa_input: [2560, 1085] first4: 0.032149 -0.047514 0.103166 -0.134958 [Debug] layer0_q_after_rope: [128, 32] first4: -0.839122 -2.228545 -2.098012 0.565041 [Debug] layer0_k_after_rope: [128, 8] first4: 1.599450 4.265841 -0.491892 5.391529 [Debug] layer0_sa_output: [2560, 1085] first4: 1.599450 4.265841 -0.491892 5.391529 [Debug] layer0_attn_out: [4096, 1085] first4: -0.839122 -2.228545 -2.098012 0.565041 [Debug] layer0_after_self_attn: [2560, 1085] first4: 0.478263 -2.237561 -0.125057 -2.763805 [Debug] layer0_after_cross_attn: [2560, 1085] first4: 0.361870 -1.976914 0.028454 -3.570030 [Debug] hidden_after_layer0: [2560, 1085] first4: 2.114879 -2.339164 233.534317 -3.539886 [Debug] hidden_after_layer6: [2560, 1085] first4: -6.125286 -2.177757 308.441315 -12.089705 [Debug] hidden_after_layer12: [2560, 1085] first4: -12.196932 29.472122 251.589767 28.293297 [Debug] hidden_after_layer18: [2560, 1085] first4: 43.714672 12.571980 253.607864 5.532092 [Debug] hidden_after_layer31: [2560, 1085] first4: -33.216412 -231.121124 -161.159271 156.747391 [Debug] dit_step0_vt: [2170, 64] first4: -1.126410 1.704001 0.905653 1.397307 [Debug] dit_step0_xt: [2170, 64] first4: 0.245536 2.078795 -0.213041 0.784142 [DiT] Step 1/8 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.740133 2.459381 0.807066 1.063587 [Debug] dit_step1_xt: [2170, 64] first4: 0.285907 1.944647 -0.257063 0.726128 [DiT] Step 2/8 t=0.955 [Debug] dit_step2_vt: [2170, 64] first4: -1.239678 1.556239 1.403674 1.257949 [Debug] dit_step2_xt: [2170, 64] first4: 0.368552 1.840898 -0.350641 0.642265 [DiT] Step 3/8 t=0.900 [Debug] dit_step3_vt: [2170, 64] first4: -0.392111 1.356317 0.932640 0.923845 [Debug] dit_step3_xt: [2170, 64] first4: 0.401228 1.727872 -0.428361 0.565278 [DiT] Step 4/8 t=0.833 [Debug] dit_step4_vt: [2170, 64] first4: -0.493893 1.416264 1.069612 0.856219 [Debug] dit_step4_xt: [2170, 64] first4: 0.454146 1.576129 -0.542962 0.473540 [DiT] Step 5/8 t=0.750 [Debug] dit_step5_vt: [2170, 64] first4: 0.201490 2.548364 0.771721 0.741034 [Debug] dit_step5_xt: [2170, 64] first4: 0.425361 1.212077 -0.653208 0.367678 [DiT] Step 6/8 t=0.643 [Debug] dit_step6_vt: [2170, 64] first4: 0.720298 2.289849 0.560320 0.600286 [Debug] dit_step6_xt: [2170, 64] first4: 0.281302 0.754107 -0.765272 0.247621 [DiT] Step 7/8 t=0.500 [Debug] dit_step7_vt: [2170, 64] first4: -1.544904 2.480084 1.128248 0.245974 [Debug] dit_x0: [2170, 64] first4: 0.744773 0.010082 -1.103747 0.173829 [DiT] Step 8/8 t=0.300 [DiT-Generate] Total: 74231.4 ms (74231.4 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.744773 0.010082 -1.103747 0.173829 [Store] Unload DiT (2801.1 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: 710 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: 29215.2 ms [Debug] vae_audio: [2, 4166400] first4: 0.001260 0.003361 0.003339 0.002933 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 542 ms (160.22x realtime), 32 threads [MP3] Wrote ggml-xl-turbo/request00.mp3 [Ace-Synth] All done 2026-07-12 09:03:14.820 | 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 0.999097 detok_output 0.999843 context 0.999900 noise 1.000000 temb_t 0.999877 hidden_after_proj_in 0.999954 enc_after_cond_emb 0.999193 layer0_sa_output 0.999445 hidden_after_layer0 0.999822 hidden_after_layer6 0.999563 hidden_after_layer12 0.998939 hidden_after_layer18 0.997982 hidden_after_layer23 0.998429 dit_step0_vt 0.998342 dit_step0_xt 1.000000 dit_step5_vt 0.998480 dit_step5_xt 0.999965 dit_step10_vt 0.997784 dit_step10_xt 0.999876 dit_step15_vt 0.995942 dit_step15_xt 0.999668 dit_step20_vt 0.992349 dit_step20_xt 0.999155 dit_step25_vt 0.986975 dit_step25_xt 0.998145 dit_step30_vt 0.980212 dit_step30_xt 0.996424 dit_step35_vt 0.973129 dit_step35_xt 0.994167 dit_step40_vt 0.968872 dit_step40_xt 0.991858 dit_step45_vt 0.973864 dit_step45_xt 0.990212 dit_step49_vt 0.981917 dit_x0 0.989649 vae_audio 0.953041 vae_audio (STFT cosine) 0.979590 [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 0.019056 0.001597 -0.001648 0.978528 -0.001619 0.978872 dit_step5_xt 0.999965 0.068526 0.005859 -0.008321 0.885208 -0.008480 0.883811 dit_step10_xt 0.999876 0.093556 0.009715 -0.015148 0.801492 -0.015075 0.802324 dit_step15_xt 0.999668 0.157459 0.014318 -0.022024 0.731200 -0.021933 0.731304 dit_step20_xt 0.999155 0.370411 0.020712 -0.028989 0.678623 -0.028882 0.679066 dit_step25_xt 0.998145 0.631030 0.028700 -0.036072 0.648047 -0.035643 0.650780 dit_step30_xt 0.996424 0.905264 0.039002 -0.043191 0.642760 -0.042577 0.647107 dit_step35_xt 0.994167 1.199536 0.051144 -0.050283 0.663609 -0.049471 0.669256 dit_step40_xt 0.991858 1.478626 0.064591 -0.057379 0.708300 -0.056532 0.715783 dit_step45_xt 0.990212 1.717842 0.077338 -0.064510 0.772567 -0.063533 0.780575 [Xl-turbo] steps=8, shift=3.0 | acestep-v15-xl-turbo-Q5_K_M.gguf [GGML] Running acestep-v15-xl-turbo-Q5_K_M.gguf... [GGML] Done, 47 dump files [Python] Initializing acestep-v15-xl-turbo... Loading checkpoint shards: 0%| | 0/4 [00:00 1.0 (turbo does not use CFG). 2026-07-12 09:03:17.202 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 09:03:17.202 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 09:03:17.202 | INFO | acestep.core.generation.handler.generate_music_request:_prepare_reference_and_source_audio:179 - [generate_music] cover task: no src_audio but audio codes provided, proceeding with codes 2026-07-12 09:03:17.205 | INFO | acestep.core.generation.handler.generate_music:_vram_preflight_check:156 - [generate_music] VRAM pre-flight: 76.75 GB free, ~1.23 GB needed (batch=1, duration=88s, mode=xl_turbo). 2026-07-12 09:03:17.210 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 09:03:17.215 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_precomputed_lm_hints:31 - [generate_music] Decoding audio codes for LM hints for item 0... 2026-07-12 09:03:17.217 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 09:03:17.217 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 09:03:17.217 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 09:03:17.217 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:122 - text_prompt: # Instruction Generate audio semantic tokens based on the given conditions: # Caption An upbeat and anthemic pop-rock track driven by bright, slightly overdriven # Metas - bpm: 83 - timesignature: 4 - keyscale: G major - duration: 88 seconds <|endoftext|> 2026-07-12 09:03:17.217 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 09:03:17.217 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:124 - lyrics_text: # Languages fr # Lyric # Lyric [Intro - Guitar Riff] [Verse 1] Dans le monde des tutos virtuels G ta toise en nouvelle passion Avec Ggendoline et PumbΓ© Γ  midi La communautΓ©, c'est l'unitΓ© Quel joie, une clΓ© [Chorus] Dans le monde des tutos virtuels GΓ’ndoline et PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner [Guitar Solo] [Verse 2] Dans le monde des tutos virtuels GΓ’ndoline, PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner<|endoftext|> 2026-07-12 09:03:17.217 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 09:03:17.221 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 09:03:17.228 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 09:03:17.228 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 09:03:17.235 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)... 2026-07-12 09:03:17.241 | INFO | acestep.models.common.dcw_correction:__init__:98 - [DCW] Active β€” mode=double, scaler=0.0500, high_scaler=0.0200, wavelet='haar' 2026-07-12 09:03:17.787 | INFO | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:42 - [generate_music] Model generation completed. Decoding latents... 2026-07-12 09:03:17.788 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:64 - [generate_music] pred_latents: torch.Size([1, 2170, 64]), dtype=torch.bfloat16 2026-07-12 09:03:17.788 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:65 - [generate_music] time_costs: {'encoder_time_cost': 0.006441354751586914, 'diffusion_time_cost': 0.5448832511901855, 'diffusion_per_step_time_cost': 0.0681104063987732, 'total_time_cost': 0.5513246059417725, 'offload_time_cost': 0.0} 2026-07-12 09:03:17.810 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:127 - [generate_music] Decoding latents with VAE... 2026-07-12 09:03:17.813 | 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 09:03:17.813 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:154 - [generate_music] Effective free VRAM before VAE decode: 76.65 GB 2026-07-12 09:03:17.813 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:172 - [generate_music] Using tiled VAE decode to reduce VRAM usage... 2026-07-12 09:03:17.813 | DEBUG | acestep.core.generation.handler.memory_utils:_get_auto_decode_chunk_size:108 - [_get_auto_decode_chunk_size] Effective free VRAM: 76.65 GB 2026-07-12 09:03:17.813 | DEBUG | acestep.core.generation.handler.memory_utils:_should_offload_wav_to_cpu:131 - [_should_offload_wav_to_cpu] Effective free VRAM: 76.65 GB 2026-07-12 09:03:17.813 | INFO | acestep.core.generation.handler.vae_decode:tiled_decode:56 - [tiled_decode] chunk_size=512, offload_wav_to_cpu=False, latents_shape=torch.Size([1, 64, 2170]) 2026-07-12 09:03:18.088 | DEBUG | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:193 - [generate_music] After VAE decode: allocated=17.21GB, max=18.50GB 2026-07-12 09:03:18.289 | INFO | acestep.core.generation.handler.generate_music_payload:_build_generate_music_success_payload:38 - [generate_music] VAE decode completed. Preparing audio tensors... 2026-07-12 09:03:18.293 | 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-Q5_K_M.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-Q5_K_M.gguf: 830 tensors, data at offset 69056 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-sft-Q5_K_M.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: 230 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-Q5_K_M.gguf: 830 tensors, data at offset 69056 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K fused, V separate [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K fused, V separate [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 141 tensors, 416.2 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L, CLS), text_proj, null_cond [Store] Load CondEnc: 307 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, 120.6 ms [Debug] enc_hidden: [238, 2048] first4: 0.688062 -0.020657 -0.051642 0.022549 [Store] Unload CondEnc (416.2 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-Q5_K_M.gguf: 830 tensors, data at offset 69056 [WeightCtx] Loaded 30 tensors, 73.2 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 65 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 423.7 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.129311 1.458194 0.298132 -0.651512 [Store] Unload FSQ-Detok (73.2 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: -0.129311 1.458194 0.298132 -0.651512 [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-Q5_K_M.gguf: 830 tensors, data at offset 69056 [DiT] Self-attn: Q+K fused, V separate [DiT] Cross-attn: all separate [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 630 tensors, 2801.1 MB into backend [Load] DiT: 32 layers, H=2560, Nh=32/8, D=128 [Store] Load DiT: 2079 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2729 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [15360] first4: 0.004454 0.088804 0.077117 -0.035327 [Debug] temb: [2560] first4: 0.010106 -0.007940 -0.006171 0.004931 [Debug] temb_t: [2560] first4: 0.008579 -0.008000 -0.006857 0.003932 [Debug] temb_r: [2560] first4: 0.001526 0.000060 0.000686 0.000999 [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: 0.028611 -0.079612 0.086698 -0.070769 [Debug] temb_lin1_r: [2560] first4: 0.006506 -0.006323 -0.000918 -0.013460 [Debug] hidden_after_proj_in: [2560, 1085] first4: 0.342082 -0.499954 0.107260 -0.205408 [Debug] proj_in_input: [192, 2170] first4: -0.129311 1.458194 0.298132 -0.651512 [Debug] enc_after_cond_emb: [2560, 238] first4: 0.058434 0.658213 0.110100 0.865776 [Debug] layer0_sa_input: [2560, 1085] first4: 0.029444 -0.037461 0.102438 -0.098226 [Debug] layer0_q_after_rope: [128, 32] first4: -0.869956 -2.039738 -2.888869 0.733576 [Debug] layer0_k_after_rope: [128, 8] first4: 1.885306 4.325730 -0.780136 7.750941 [Debug] layer0_sa_output: [2560, 1085] first4: 1.885306 4.325730 -0.780136 7.750941 [Debug] layer0_attn_out: [4096, 1085] first4: -0.869956 -2.039738 -2.888869 0.733576 [Debug] layer0_after_self_attn: [2560, 1085] first4: 0.461121 -2.160442 -0.468358 -4.108160 [Debug] layer0_after_cross_attn: [2560, 1085] first4: 0.295444 -1.889656 -0.392346 -4.112534 [Debug] hidden_after_layer0: [2560, 1085] first4: -1.380714 -1.249189 240.959122 -3.969363 [Debug] hidden_after_layer6: [2560, 1085] first4: -7.057535 3.304931 301.314941 -21.764675 [Debug] hidden_after_layer12: [2560, 1085] first4: -21.769068 37.141205 219.646042 14.473962 [Debug] hidden_after_layer18: [2560, 1085] first4: 12.172172 -14.774710 226.105438 20.880741 [Debug] hidden_after_layer31: [2560, 1085] first4: 64.596344 -116.611908 -3.008900 78.931442 [Debug] dit_step0_vt: [2170, 64] first4: -0.346020 2.224401 0.054148 1.693466 [Debug] dit_step0_xt: [2170, 64] first4: 0.201256 2.111762 -0.172958 0.813787 [DiT] Step 1/50 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.367564 2.193091 0.096830 1.562009 [Debug] dit_step1_xt: [2170, 64] first4: 0.208608 2.067900 -0.174895 0.782547 [DiT] Step 2/50 t=0.980 [Debug] dit_step2_vt: [2170, 64] first4: -0.348577 2.168818 0.082129 1.537476 [Debug] dit_step2_xt: [2170, 64] first4: 0.215579 2.024524 -0.176537 0.751797 [DiT] Step 3/50 t=0.960 [Debug] dit_step3_vt: [2170, 64] first4: -0.313320 2.119481 0.071088 1.576522 [Debug] dit_step3_xt: [2170, 64] first4: 0.221846 1.982134 -0.177959 0.720267 [DiT] Step 4/50 t=0.940 [Debug] dit_step4_vt: [2170, 64] first4: -0.295707 2.064621 0.070415 1.569607 [Debug] dit_step4_xt: [2170, 64] first4: 0.227760 1.940842 -0.179367 0.688875 [DiT] Step 5/50 t=0.920 [Debug] dit_step5_vt: [2170, 64] first4: -0.277902 2.038022 0.090165 1.573716 [Debug] dit_step5_xt: [2170, 64] first4: 0.233318 1.900081 -0.181171 0.657400 [DiT] Step 6/50 t=0.900 [Debug] dit_step6_vt: [2170, 64] first4: -0.282423 2.042879 0.118506 1.584817 [Debug] dit_step6_xt: [2170, 64] first4: 0.238966 1.859224 -0.183541 0.625704 [DiT] Step 7/50 t=0.880 [Debug] dit_step7_vt: [2170, 64] first4: -0.271331 1.993357 0.157914 1.598758 [Debug] dit_step7_xt: [2170, 64] first4: 0.244393 1.819357 -0.186699 0.593729 [DiT] Step 8/50 t=0.860 [Debug] dit_step8_vt: [2170, 64] first4: -0.295205 1.933540 0.192945 1.588760 [Debug] dit_step8_xt: [2170, 64] first4: 0.250297 1.780686 -0.190558 0.561954 [DiT] Step 9/50 t=0.840 [Debug] dit_step9_vt: [2170, 64] first4: -0.316605 1.868905 0.167400 1.574687 [Debug] dit_step9_xt: [2170, 64] first4: 0.256629 1.743308 -0.193906 0.530460 [DiT] Step 10/50 t=0.820 [Debug] dit_step10_vt: [2170, 64] first4: -0.332900 1.802391 0.151333 1.570688 [Debug] dit_step10_xt: [2170, 64] first4: 0.263287 1.707260 -0.196933 0.499046 [DiT] Step 11/50 t=0.800 [Debug] dit_step11_vt: [2170, 64] first4: -0.337600 1.764247 0.163139 1.546635 [Debug] dit_step11_xt: [2170, 64] first4: 0.270039 1.671975 -0.200195 0.468113 [DiT] Step 12/50 t=0.780 [Debug] dit_step12_vt: [2170, 64] first4: -0.340541 1.713530 0.150117 1.528393 [Debug] dit_step12_xt: [2170, 64] first4: 0.276850 1.637704 -0.203198 0.437546 [DiT] Step 13/50 t=0.760 [Debug] dit_step13_vt: [2170, 64] first4: -0.315612 1.666525 0.087107 1.516710 [Debug] dit_step13_xt: [2170, 64] first4: 0.283162 1.604374 -0.204940 0.407211 [DiT] Step 14/50 t=0.740 [Debug] dit_step14_vt: [2170, 64] first4: -0.319458 1.609888 0.074614 1.503448 [Debug] dit_step14_xt: [2170, 64] first4: 0.289551 1.572176 -0.206432 0.377142 [DiT] Step 15/50 t=0.720 [Debug] dit_step15_vt: [2170, 64] first4: -0.324296 1.569885 0.046346 1.491339 [Debug] dit_step15_xt: [2170, 64] first4: 0.296037 1.540779 -0.207359 0.347316 [DiT] Step 16/50 t=0.700 [Debug] dit_step16_vt: [2170, 64] first4: -0.287870 1.518337 0.051558 1.497549 [Debug] dit_step16_xt: [2170, 64] first4: 0.301795 1.510412 -0.208390 0.317365 [DiT] Step 17/50 t=0.680 [Debug] dit_step17_vt: [2170, 64] first4: -0.239368 1.471347 0.046255 1.487620 [Debug] dit_step17_xt: [2170, 64] first4: 0.306582 1.480985 -0.209315 0.287612 [DiT] Step 18/50 t=0.660 [Debug] dit_step18_vt: [2170, 64] first4: -0.199585 1.418081 -0.011760 1.461504 [Debug] dit_step18_xt: [2170, 64] first4: 0.310574 1.452623 -0.209080 0.258382 [DiT] Step 19/50 t=0.640 [Debug] dit_step19_vt: [2170, 64] first4: -0.152128 1.367533 -0.022630 1.480447 [Debug] dit_step19_xt: [2170, 64] first4: 0.313616 1.425273 -0.208627 0.228773 [DiT] Step 20/50 t=0.620 [Debug] dit_step20_vt: [2170, 64] first4: -0.129373 1.336968 -0.040040 1.478129 [Debug] dit_step20_xt: [2170, 64] first4: 0.316204 1.398533 -0.207827 0.199211 [DiT] Step 21/50 t=0.600 [Debug] dit_step21_vt: [2170, 64] first4: -0.082906 1.279153 -0.024081 1.472304 [Debug] dit_step21_xt: [2170, 64] first4: 0.317862 1.372950 -0.207345 0.169765 [DiT] Step 22/50 t=0.580 [Debug] dit_step22_vt: [2170, 64] first4: -0.042462 1.237696 -0.035901 1.446045 [Debug] dit_step22_xt: [2170, 64] first4: 0.318711 1.348196 -0.206627 0.140844 [DiT] Step 23/50 t=0.560 [Debug] dit_step23_vt: [2170, 64] first4: -0.065737 1.167129 -0.062472 1.415871 [Debug] dit_step23_xt: [2170, 64] first4: 0.320026 1.324854 -0.205378 0.112526 [DiT] Step 24/50 t=0.540 [Debug] dit_step24_vt: [2170, 64] first4: -0.048890 1.157182 -0.059737 1.401962 [Debug] dit_step24_xt: [2170, 64] first4: 0.321004 1.301710 -0.204183 0.084487 [DiT] Step 25/50 t=0.520 [Debug] dit_step25_vt: [2170, 64] first4: -0.019443 1.048451 -0.083332 1.382850 [Debug] dit_step25_xt: [2170, 64] first4: 0.321392 1.280741 -0.202516 0.056830 [DiT] Step 26/50 t=0.500 [Debug] dit_step26_vt: [2170, 64] first4: 0.011140 1.013344 -0.073887 1.323753 [Debug] dit_step26_xt: [2170, 64] first4: 0.321170 1.260474 -0.201038 0.030355 [DiT] Step 27/50 t=0.480 [Debug] dit_step27_vt: [2170, 64] first4: -0.018643 0.980538 -0.114409 1.314877 [Debug] dit_step27_xt: [2170, 64] first4: 0.321542 1.240863 -0.198750 0.004057 [DiT] Step 28/50 t=0.460 [Debug] dit_step28_vt: [2170, 64] first4: -0.054475 0.908593 -0.154670 1.326807 [Debug] dit_step28_xt: [2170, 64] first4: 0.322632 1.222691 -0.195657 -0.022479 [DiT] Step 29/50 t=0.440 [Debug] dit_step29_vt: [2170, 64] first4: -0.052488 0.845439 -0.135951 1.274078 [Debug] dit_step29_xt: [2170, 64] first4: 0.323682 1.205783 -0.192938 -0.047960 [DiT] Step 30/50 t=0.420 [Debug] dit_step30_vt: [2170, 64] first4: -0.050046 0.779631 -0.131362 1.262460 [Debug] dit_step30_xt: [2170, 64] first4: 0.324683 1.190190 -0.190311 -0.073209 [DiT] Step 31/50 t=0.400 [Debug] dit_step31_vt: [2170, 64] first4: -0.028920 0.699645 -0.114697 1.235100 [Debug] dit_step31_xt: [2170, 64] first4: 0.325261 1.176197 -0.188017 -0.097911 [DiT] Step 32/50 t=0.380 [Debug] dit_step32_vt: [2170, 64] first4: -0.017474 0.592432 -0.135993 1.175098 [Debug] dit_step32_xt: [2170, 64] first4: 0.325611 1.164348 -0.185297 -0.121413 [DiT] Step 33/50 t=0.360 [Debug] dit_step33_vt: [2170, 64] first4: -0.060590 0.516016 -0.144490 1.162746 [Debug] dit_step33_xt: [2170, 64] first4: 0.326822 1.154028 -0.182407 -0.144668 [DiT] Step 34/50 t=0.340 [Debug] dit_step34_vt: [2170, 64] first4: -0.035622 0.437117 -0.170617 1.154109 [Debug] dit_step34_xt: [2170, 64] first4: 0.327535 1.145286 -0.178995 -0.167751 [DiT] Step 35/50 t=0.320 [Debug] dit_step35_vt: [2170, 64] first4: -0.070583 0.339209 -0.167892 1.121394 [Debug] dit_step35_xt: [2170, 64] first4: 0.328946 1.138502 -0.175637 -0.190178 [DiT] Step 36/50 t=0.300 [Debug] dit_step36_vt: [2170, 64] first4: -0.072918 0.273496 -0.118026 1.061656 [Debug] dit_step36_xt: [2170, 64] first4: 0.330405 1.133032 -0.173276 -0.211412 [DiT] Step 37/50 t=0.280 [Debug] dit_step37_vt: [2170, 64] first4: -0.096986 0.144655 -0.153114 1.054976 [Debug] dit_step37_xt: [2170, 64] first4: 0.332344 1.130139 -0.170214 -0.232511 [DiT] Step 38/50 t=0.260 [Debug] dit_step38_vt: [2170, 64] first4: -0.150667 0.026723 -0.079812 1.017742 [Debug] dit_step38_xt: [2170, 64] first4: 0.335358 1.129604 -0.168618 -0.252866 [DiT] Step 39/50 t=0.240 [Debug] dit_step39_vt: [2170, 64] first4: -0.146516 -0.118185 -0.136240 0.958452 [Debug] dit_step39_xt: [2170, 64] first4: 0.338288 1.131968 -0.165893 -0.272035 [DiT] Step 40/50 t=0.220 [Debug] dit_step40_vt: [2170, 64] first4: -0.224715 -0.168659 -0.125339 0.923105 [Debug] dit_step40_xt: [2170, 64] first4: 0.342782 1.135341 -0.163386 -0.290497 [DiT] Step 41/50 t=0.200 [Debug] dit_step41_vt: [2170, 64] first4: -0.202036 -0.297379 -0.077384 0.795588 [Debug] dit_step41_xt: [2170, 64] first4: 0.346823 1.141289 -0.161839 -0.306409 [DiT] Step 42/50 t=0.180 [Debug] dit_step42_vt: [2170, 64] first4: -0.199897 -0.414235 -0.017018 0.799910 [Debug] dit_step42_xt: [2170, 64] first4: 0.350821 1.149573 -0.161498 -0.322407 [DiT] Step 43/50 t=0.160 [Debug] dit_step43_vt: [2170, 64] first4: -0.247902 -0.500425 -0.032442 0.739392 [Debug] dit_step43_xt: [2170, 64] first4: 0.355779 1.159582 -0.160849 -0.337195 [DiT] Step 44/50 t=0.140 [Debug] dit_step44_vt: [2170, 64] first4: -0.274952 -0.585648 0.012632 0.740135 [Debug] dit_step44_xt: [2170, 64] first4: 0.361278 1.171295 -0.161102 -0.351997 [DiT] Step 45/50 t=0.120 [Debug] dit_step45_vt: [2170, 64] first4: -0.319255 -0.641395 0.070521 0.675308 [Debug] dit_step45_xt: [2170, 64] first4: 0.367663 1.184123 -0.162512 -0.365504 [DiT] Step 46/50 t=0.100 [Debug] dit_step46_vt: [2170, 64] first4: -0.344289 -0.694185 0.093769 0.603600 [Debug] dit_step46_xt: [2170, 64] first4: 0.374549 1.198006 -0.164388 -0.377576 [DiT] Step 47/50 t=0.080 [Debug] dit_step47_vt: [2170, 64] first4: -0.375019 -0.763885 0.153348 0.571467 [Debug] dit_step47_xt: [2170, 64] first4: 0.382049 1.213284 -0.167455 -0.389005 [DiT] Step 48/50 t=0.060 [Debug] dit_step48_vt: [2170, 64] first4: -0.402479 -0.858725 0.238471 0.524461 [Debug] dit_step48_xt: [2170, 64] first4: 0.390099 1.230459 -0.172224 -0.399494 [DiT] Step 49/50 t=0.040 [Debug] dit_step49_vt: [2170, 64] first4: -0.403422 -0.847802 0.176242 0.558820 [Debug] dit_x0: [2170, 64] first4: 0.398167 1.247415 -0.175749 -0.410671 [DiT] Step 50/50 t=0.020 [DiT-Generate] Total: 465989.1 ms (465989.1 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.398167 1.247415 -0.175749 -0.410671 [Store] Unload DiT (2801.1 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: 712 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: 27147.7 ms [Debug] vae_audio: [2, 4166400] first4: -0.001544 -0.000835 -0.000944 -0.000429 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 440 ms (197.37x realtime), 32 threads [MP3] Wrote ggml-xl-sft/request00.mp3 [Ace-Synth] All done 2026-07-12 09:11:36.942 | 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 0.998858 detok_output 0.999843 context 0.999900 noise 1.000000 temb_t 0.999905 hidden_after_proj_in 0.999931 enc_after_cond_emb 0.998778 layer0_sa_output 0.998917 hidden_after_layer0 0.999383 hidden_after_layer6 0.999592 hidden_after_layer12 0.994932 hidden_after_layer18 0.995408 hidden_after_layer31 0.987959 dit_step0_vt 0.912834 dit_step0_xt 0.999843 dit_step1_vt 0.922537 dit_step1_xt 0.999511 dit_step2_vt 0.920703 dit_step2_xt 0.998660 dit_step3_vt 0.917007 dit_step3_xt 0.996603 dit_step4_vt 0.909719 dit_step4_xt 0.991474 dit_step5_vt 0.902367 dit_step5_xt 0.979430 dit_step6_vt 0.894078 dit_step6_xt 0.955641 dit_step7_vt 0.873333 dit_x0 0.917759 vae_audio 0.702575 vae_audio (STFT cosine) 0.918703 [Xl-turbo] Error growth GGML vs Python stage cos max_err mean_err mean_A std_A mean_B std_B dit_step0_xt 0.999843 0.229904 0.012558 -0.002935 0.978421 -0.002721 0.976534 dit_step1_xt 0.999511 0.278322 0.021896 -0.005850 0.952211 -0.005567 0.949004 dit_step2_xt 0.998660 0.442772 0.034848 -0.009658 0.923813 -0.009330 0.918931 dit_step3_xt 0.996603 0.780983 0.052739 -0.015198 0.893576 -0.014418 0.887241 dit_step4_xt 0.991474 1.369528 0.079978 -0.022763 0.865948 -0.021453 0.857796 dit_step5_xt 0.979430 2.043327 0.121381 -0.033975 0.850794 -0.032240 0.840033 dit_step6_xt 0.955641 2.876475 0.184187 -0.051083 0.877629 -0.049194 0.863964 [Xl-sft] steps=50, shift=1.0 | acestep-v15-xl-sft-Q5_K_M.gguf [GGML] Running acestep-v15-xl-sft-Q5_K_M.gguf... [GGML] Done, 131 dump files [Python] Initializing acestep-v15-xl-sft... Loading checkpoint shards: 0%| | 0/4 [00:00 2026-07-12 09:11:41.672 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 09:11:41.672 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:124 - lyrics_text: # Languages fr # Lyric # Lyric [Intro - Guitar Riff] [Verse 1] Dans le monde des tutos virtuels G ta toise en nouvelle passion Avec Ggendoline et PumbΓ© Γ  midi La communautΓ©, c'est l'unitΓ© Quel joie, une clΓ© [Chorus] Dans le monde des tutos virtuels GΓ’ndoline et PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner [Guitar Solo] [Verse 2] Dans le monde des tutos virtuels GΓ’ndoline, PumbΓ© Γ  midi Une famille Γ  connecter, c'est vrai D'un enfant qui voit toi fusionner<|endoftext|> 2026-07-12 09:11:41.672 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 09:11:41.675 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 09:11:41.684 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 09:11:41.684 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 09:11:41.690 | 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