[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-Q6_K.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-Q6_K.gguf: 678 tensors, data at offset 56864 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-turbo-Q6_K.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: 5615 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-Q6_K.gguf: 678 tensors, data at offset 56864 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 140 tensors, 476.3 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L), text_proj, null_cond [Store] Load CondEnc: 315 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, 94.9 ms [Debug] enc_hidden: [238, 2048] first4: 1.762379 -0.051814 -0.131966 0.057631 [Store] Unload CondEnc (476.3 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-Q6_K.gguf: 678 tensors, data at offset 56864 [WeightCtx] Loaded 30 tensors, 82.2 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 53 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 361.4 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.151355 1.462444 0.326907 -0.627213 [Store] Unload FSQ-Detok (82.2 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: -0.151355 1.462444 0.326907 -0.627213 [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-Q6_K.gguf: 678 tensors, data at offset 56864 [DiT] Self-attn: Q+K+V fused [DiT] Cross-attn: Q+K+V fused [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 478 tensors, 1237.2 MB into backend [Load] DiT: 24 layers, H=2048, Nh=16/8, D=128 [Store] Load DiT: 886 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2129 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [12288] first4: 0.261809 -0.161156 -0.099489 0.050901 [Debug] temb: [2048] first4: 0.000441 -0.132284 -0.035603 0.064823 [Debug] temb_t: [2048] first4: 0.001519 0.026983 -0.052936 0.063921 [Debug] temb_r: [2048] first4: -0.001078 -0.159268 0.017333 0.000903 [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: -0.049242 -0.050737 -0.017494 -0.036973 [Debug] temb_lin1_r: [2048] first4: -0.014408 -0.020609 -0.015729 0.003875 [Debug] hidden_after_proj_in: [2048, 1085] first4: -1.041706 -0.935163 0.543316 0.447904 [Debug] proj_in_input: [192, 2170] first4: -0.151355 1.462444 0.326907 -0.627213 [Debug] enc_after_cond_emb: [2048, 238] first4: -0.166439 0.831665 0.328897 -0.589582 [Debug] layer0_sa_input: [2048, 1085] first4: -0.719262 -0.743265 -0.048909 0.260726 [Debug] layer0_q_after_rope: [128, 16] first4: -1.546695 -1.029571 0.220500 0.458906 [Debug] layer0_k_after_rope: [128, 8] first4: -0.166439 0.831665 0.328897 -0.589582 [Debug] layer0_sa_output: [2048, 1085] first4: -1.511177 0.212656 -0.330983 0.523252 [Debug] layer0_attn_out: [2048, 1085] first4: -1.546695 -1.029571 0.220500 0.458906 [Debug] layer0_after_self_attn: [2048, 1085] first4: -1.546695 -1.029571 0.220500 0.458906 [Debug] layer0_after_cross_attn: [2048, 1085] first4: -1.609587 -0.798885 -0.285115 0.500374 [Debug] hidden_after_layer0: [2048, 1085] first4: -9.238791 0.594274 52.893948 -0.948797 [Debug] hidden_after_layer6: [2048, 1085] first4: -21.246397 -0.218955 36.391987 -4.624691 [Debug] hidden_after_layer12: [2048, 1085] first4: -15.351803 -16.536158 76.883438 31.149061 [Debug] hidden_after_layer18: [2048, 1085] first4: -28.788742 13.380124 63.779480 20.173618 [Debug] hidden_after_layer23: [2048, 1085] first4: -20.930138 54.459087 193.014542 140.836411 [Debug] dit_step0_vt: [2170, 64] first4: 0.096821 1.129415 0.285259 2.376315 [Debug] dit_step0_xt: [2170, 64] first4: 0.189935 2.104913 -0.184841 0.739642 [DiT] Step 1/8 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.109089 1.309798 -0.244168 1.987816 [Debug] dit_step1_xt: [2170, 64] first4: 0.195885 2.033469 -0.171523 0.631216 [DiT] Step 2/8 t=0.955 [Debug] dit_step2_vt: [2170, 64] first4: 0.094821 1.245678 0.101010 2.413914 [Debug] dit_step2_xt: [2170, 64] first4: 0.189564 1.950424 -0.178257 0.470288 [DiT] Step 3/8 t=0.900 [Debug] dit_step3_vt: [2170, 64] first4: 0.313540 1.102525 0.261468 2.697613 [Debug] dit_step3_xt: [2170, 64] first4: 0.163436 1.858547 -0.200046 0.245487 [DiT] Step 4/8 t=0.833 [Debug] dit_step4_vt: [2170, 64] first4: 0.285723 0.994373 0.111937 2.733400 [Debug] dit_step4_xt: [2170, 64] first4: 0.132822 1.752007 -0.212039 -0.047377 [DiT] Step 5/8 t=0.750 [Debug] dit_step5_vt: [2170, 64] first4: 0.362832 0.887874 -0.305495 2.771905 [Debug] dit_step5_xt: [2170, 64] first4: 0.080989 1.625168 -0.168397 -0.443364 [DiT] Step 6/8 t=0.643 [Debug] dit_step6_vt: [2170, 64] first4: 0.296376 0.640049 -0.759461 2.749637 [Debug] dit_step6_xt: [2170, 64] first4: 0.021714 1.497158 -0.016505 -0.993291 [DiT] Step 7/8 t=0.500 [Debug] dit_step7_vt: [2170, 64] first4: 0.215550 0.167503 -1.350311 2.964794 [Debug] dit_x0: [2170, 64] first4: -0.042951 1.446907 0.388589 -1.882729 [DiT] Step 8/8 t=0.300 [DiT-Generate] Total: 21489.5 ms (21489.5 ms/sample) [Debug] dit_output: [2170, 64] first4: -0.042951 1.446907 0.388589 -1.882729 [Store] Unload DiT (1237.2 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: 27507.6 ms [Debug] vae_audio: [2, 4166400] first4: 0.000737 0.001471 0.001249 0.001782 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 519 ms (167.28x realtime), 32 threads [MP3] Wrote ggml-turbo/request00.mp3 [Ace-Synth] All done 2026-07-12 08:45:19.863 | 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 08:45:21.959 | WARNING | acestep.training.trainer::40 - bitsandbytes not installed. Using standard AdamW. 2026-07-12 08:45:21.964 | 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 08:45:22.052 | 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 08:45:24.975 | 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 08:45:24.975 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 08:45:24.975 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 08:45:24.975 | 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 08:45:24.978 | 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 08:45:24.984 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 08:45:25.193 | 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 08:45:25.196 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 08:45:25.196 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 08:45:25.196 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 08:45:25.196 | 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 08:45:25.196 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 08:45:25.196 | 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 08:45:25.196 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 08:45:25.203 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 08:45:25.217 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 08:45:25.218 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 08:45:25.242 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)... 2026-07-12 08:45:25.250 | 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 08:45:25.355 | 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 08:45:25.579 | INFO | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:42 - [generate_music] Model generation completed. Decoding latents... 2026-07-12 08:45:25.580 | 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 08:45:25.580 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:65 - [generate_music] time_costs: {'encoder_time_cost': 0.007036685943603516, 'diffusion_time_cost': 0.32941627502441406, 'diffusion_per_step_time_cost': 0.04117703437805176, 'total_time_cost': 0.3364529609680176, 'offload_time_cost': 0.0} 2026-07-12 08:45:25.594 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:127 - [generate_music] Decoding latents with VAE... 2026-07-12 08:45:25.596 | 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 08:45:25.596 | 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 08:45:25.596 | 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 08:45:25.596 | 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 08:45:25.597 | 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 08:45:25.597 | 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 08:45:25.879 | 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 08:45:26.038 | 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 08:45:26.041 | 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-Q6_K.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-Q6_K.gguf: 678 tensors, data at offset 56800 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-sft-Q6_K.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: 246 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-Q6_K.gguf: 678 tensors, data at offset 56800 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 140 tensors, 476.3 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L), text_proj, null_cond [Store] Load CondEnc: 315 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, 100.8 ms [Debug] enc_hidden: [238, 2048] first4: 1.762379 -0.051814 -0.131966 0.057631 [Store] Unload CondEnc (476.3 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-Q6_K.gguf: 678 tensors, data at offset 56800 [WeightCtx] Loaded 30 tensors, 82.2 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 57 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 351.1 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.151355 1.462444 0.326907 -0.627213 [Store] Unload FSQ-Detok (82.2 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: -0.151355 1.462444 0.326907 -0.627213 [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-Q6_K.gguf: 678 tensors, data at offset 56800 [DiT] Self-attn: Q+K+V fused [DiT] Cross-attn: Q+K+V fused [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 478 tensors, 1237.2 MB into backend [Load] DiT: 24 layers, H=2048, Nh=16/8, D=128 [Store] Load DiT: 917 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2129 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [12288] first4: 0.154743 -0.116957 -0.090544 0.080574 [Debug] temb: [2048] first4: -0.002145 -0.176665 0.004243 -0.002255 [Debug] temb_t: [2048] first4: -0.000777 0.003197 -0.013362 -0.002273 [Debug] temb_r: [2048] first4: -0.001369 -0.179863 0.017604 0.000017 [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: -0.041318 0.030674 0.028131 -0.025225 [Debug] temb_lin1_r: [2048] first4: 0.004272 0.006720 0.000208 -0.005103 [Debug] hidden_after_proj_in: [2048, 1085] first4: -1.092314 -0.891880 0.504853 0.441786 [Debug] proj_in_input: [192, 2170] first4: -0.151355 1.462444 0.326907 -0.627213 [Debug] enc_after_cond_emb: [2048, 238] first4: -0.193801 0.898684 0.328701 -0.595298 [Debug] layer0_sa_input: [2048, 1085] first4: -0.916144 -0.696019 -0.040361 0.292980 [Debug] layer0_q_after_rope: [128, 16] first4: -1.800593 -1.339359 -0.144539 0.381733 [Debug] layer0_k_after_rope: [128, 8] first4: -0.193801 0.898684 0.328701 -0.595298 [Debug] layer0_sa_output: [2048, 1085] first4: -1.640291 0.793311 -0.575851 0.538407 [Debug] layer0_attn_out: [2048, 1085] first4: -1.800593 -1.339359 -0.144539 0.381733 [Debug] layer0_after_self_attn: [2048, 1085] first4: -1.800593 -1.339359 -0.144539 0.381733 [Debug] layer0_after_cross_attn: [2048, 1085] first4: -1.972986 -1.027412 -0.424850 0.386348 [Debug] hidden_after_layer0: [2048, 1085] first4: -9.390988 1.432513 58.367939 -1.779012 [Debug] hidden_after_layer6: [2048, 1085] first4: -17.649006 2.919505 58.992424 -1.699171 [Debug] hidden_after_layer12: [2048, 1085] first4: -8.396528 6.754469 -18.786980 -4.312500 [Debug] hidden_after_layer18: [2048, 1085] first4: -3.990694 18.373602 -40.167282 -13.808522 [Debug] hidden_after_layer23: [2048, 1085] first4: 33.229965 65.295158 57.146408 -15.140586 [Debug] dit_step0_vt: [2170, 64] first4: -0.613155 2.547581 -0.196654 1.428258 [Debug] dit_step0_xt: [2170, 64] first4: 0.206599 2.105299 -0.167942 0.819091 [DiT] Step 1/50 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.663447 2.493828 -0.038055 1.289847 [Debug] dit_step1_xt: [2170, 64] first4: 0.219868 2.055422 -0.167181 0.793294 [DiT] Step 2/50 t=0.980 [Debug] dit_step2_vt: [2170, 64] first4: -0.674803 2.465809 0.008688 1.318933 [Debug] dit_step2_xt: [2170, 64] first4: 0.233364 2.006106 -0.167355 0.766916 [DiT] Step 3/50 t=0.960 [Debug] dit_step3_vt: [2170, 64] first4: -0.648109 2.418533 0.014945 1.320962 [Debug] dit_step3_xt: [2170, 64] first4: 0.246326 1.957735 -0.167653 0.740496 [DiT] Step 4/50 t=0.940 [Debug] dit_step4_vt: [2170, 64] first4: -0.588350 2.349323 0.002589 1.297261 [Debug] dit_step4_xt: [2170, 64] first4: 0.258093 1.910748 -0.167705 0.714551 [DiT] Step 5/50 t=0.920 [Debug] dit_step5_vt: [2170, 64] first4: -0.567034 2.293223 -0.045573 1.311477 [Debug] dit_step5_xt: [2170, 64] first4: 0.269434 1.864884 -0.166794 0.688321 [DiT] Step 6/50 t=0.900 [Debug] dit_step6_vt: [2170, 64] first4: -0.550175 2.226671 -0.074374 1.294147 [Debug] dit_step6_xt: [2170, 64] first4: 0.280437 1.820351 -0.165306 0.662439 [DiT] Step 7/50 t=0.880 [Debug] dit_step7_vt: [2170, 64] first4: -0.497449 2.172086 -0.105903 1.244451 [Debug] dit_step7_xt: [2170, 64] first4: 0.290386 1.776909 -0.163188 0.637550 [DiT] Step 8/50 t=0.860 [Debug] dit_step8_vt: [2170, 64] first4: -0.447147 2.063720 -0.107179 1.236527 [Debug] dit_step8_xt: [2170, 64] first4: 0.299329 1.735635 -0.161045 0.612819 [DiT] Step 9/50 t=0.840 [Debug] dit_step9_vt: [2170, 64] first4: -0.408917 1.991816 -0.108373 1.239699 [Debug] dit_step9_xt: [2170, 64] first4: 0.307508 1.695798 -0.158877 0.588025 [DiT] Step 10/50 t=0.820 [Debug] dit_step10_vt: [2170, 64] first4: -0.357801 1.899434 -0.079387 1.256928 [Debug] dit_step10_xt: [2170, 64] first4: 0.314664 1.657809 -0.157289 0.562886 [DiT] Step 11/50 t=0.800 [Debug] dit_step11_vt: [2170, 64] first4: -0.297573 1.819247 -0.081204 1.217842 [Debug] dit_step11_xt: [2170, 64] first4: 0.320615 1.621425 -0.155665 0.538530 [DiT] Step 12/50 t=0.780 [Debug] dit_step12_vt: [2170, 64] first4: -0.294055 1.771263 -0.102634 1.212019 [Debug] dit_step12_xt: [2170, 64] first4: 0.326496 1.585999 -0.153613 0.514289 [DiT] Step 13/50 t=0.760 [Debug] dit_step13_vt: [2170, 64] first4: -0.247233 1.678866 -0.108163 1.184444 [Debug] dit_step13_xt: [2170, 64] first4: 0.331441 1.552422 -0.151449 0.490600 [DiT] Step 14/50 t=0.740 [Debug] dit_step14_vt: [2170, 64] first4: -0.269772 1.581149 -0.121730 1.164117 [Debug] dit_step14_xt: [2170, 64] first4: 0.336836 1.520799 -0.149015 0.467318 [DiT] Step 15/50 t=0.720 [Debug] dit_step15_vt: [2170, 64] first4: -0.272701 1.488023 -0.167510 1.160755 [Debug] dit_step15_xt: [2170, 64] first4: 0.342290 1.491039 -0.145665 0.444103 [DiT] Step 16/50 t=0.700 [Debug] dit_step16_vt: [2170, 64] first4: -0.252492 1.429439 -0.180513 1.137944 [Debug] dit_step16_xt: [2170, 64] first4: 0.347340 1.462450 -0.142054 0.421344 [DiT] Step 17/50 t=0.680 [Debug] dit_step17_vt: [2170, 64] first4: -0.255146 1.360306 -0.184972 1.130484 [Debug] dit_step17_xt: [2170, 64] first4: 0.352443 1.435244 -0.138355 0.398734 [DiT] Step 18/50 t=0.660 [Debug] dit_step18_vt: [2170, 64] first4: -0.246620 1.226624 -0.254603 1.089695 [Debug] dit_step18_xt: [2170, 64] first4: 0.357376 1.410711 -0.133263 0.376940 [DiT] Step 19/50 t=0.640 [Debug] dit_step19_vt: [2170, 64] first4: -0.271630 1.150125 -0.257228 1.077862 [Debug] dit_step19_xt: [2170, 64] first4: 0.362808 1.387709 -0.128118 0.355383 [DiT] Step 20/50 t=0.620 [Debug] dit_step20_vt: [2170, 64] first4: -0.263521 1.077636 -0.267216 1.005920 [Debug] dit_step20_xt: [2170, 64] first4: 0.368079 1.366156 -0.122774 0.335265 [DiT] Step 21/50 t=0.600 [Debug] dit_step21_vt: [2170, 64] first4: -0.302119 1.022598 -0.277398 1.004931 [Debug] dit_step21_xt: [2170, 64] first4: 0.374121 1.345704 -0.117226 0.315166 [DiT] Step 22/50 t=0.580 [Debug] dit_step22_vt: [2170, 64] first4: -0.324717 0.905917 -0.281318 0.968673 [Debug] dit_step22_xt: [2170, 64] first4: 0.380615 1.327586 -0.111600 0.295793 [DiT] Step 23/50 t=0.560 [Debug] dit_step23_vt: [2170, 64] first4: -0.350317 0.777622 -0.258736 0.960743 [Debug] dit_step23_xt: [2170, 64] first4: 0.387622 1.312033 -0.106425 0.276578 [DiT] Step 24/50 t=0.540 [Debug] dit_step24_vt: [2170, 64] first4: -0.339513 0.682454 -0.318128 0.907703 [Debug] dit_step24_xt: [2170, 64] first4: 0.394412 1.298384 -0.100062 0.258424 [DiT] Step 25/50 t=0.520 [Debug] dit_step25_vt: [2170, 64] first4: -0.364719 0.586407 -0.330357 0.903476 [Debug] dit_step25_xt: [2170, 64] first4: 0.401706 1.286656 -0.093455 0.240354 [DiT] Step 26/50 t=0.500 [Debug] dit_step26_vt: [2170, 64] first4: -0.419099 0.456836 -0.324072 0.907680 [Debug] dit_step26_xt: [2170, 64] first4: 0.410088 1.277519 -0.086974 0.222201 [DiT] Step 27/50 t=0.480 [Debug] dit_step27_vt: [2170, 64] first4: -0.439269 0.343207 -0.273876 0.888646 [Debug] dit_step27_xt: [2170, 64] first4: 0.418874 1.270655 -0.081496 0.204428 [DiT] Step 28/50 t=0.460 [Debug] dit_step28_vt: [2170, 64] first4: -0.456026 0.230825 -0.293520 0.852550 [Debug] dit_step28_xt: [2170, 64] first4: 0.427994 1.266039 -0.075626 0.187377 [DiT] Step 29/50 t=0.440 [Debug] dit_step29_vt: [2170, 64] first4: -0.478737 0.145372 -0.269324 0.830974 [Debug] dit_step29_xt: [2170, 64] first4: 0.437569 1.263131 -0.070239 0.170757 [DiT] Step 30/50 t=0.420 [Debug] dit_step30_vt: [2170, 64] first4: -0.477460 0.035568 -0.253190 0.848988 [Debug] dit_step30_xt: [2170, 64] first4: 0.447118 1.262420 -0.065176 0.153777 [DiT] Step 31/50 t=0.400 [Debug] dit_step31_vt: [2170, 64] first4: -0.482763 -0.047301 -0.209945 0.843768 [Debug] dit_step31_xt: [2170, 64] first4: 0.456773 1.263366 -0.060977 0.136902 [DiT] Step 32/50 t=0.380 [Debug] dit_step32_vt: [2170, 64] first4: -0.503102 -0.202677 -0.254872 0.801592 [Debug] dit_step32_xt: [2170, 64] first4: 0.466835 1.267419 -0.055879 0.120870 [DiT] Step 33/50 t=0.360 [Debug] dit_step33_vt: [2170, 64] first4: -0.505268 -0.284653 -0.182772 0.784557 [Debug] dit_step33_xt: [2170, 64] first4: 0.476941 1.273113 -0.052224 0.105179 [DiT] Step 34/50 t=0.340 [Debug] dit_step34_vt: [2170, 64] first4: -0.557398 -0.365016 -0.246660 0.760562 [Debug] dit_step34_xt: [2170, 64] first4: 0.488089 1.280413 -0.047291 0.089968 [DiT] Step 35/50 t=0.320 [Debug] dit_step35_vt: [2170, 64] first4: -0.570670 -0.513508 -0.215129 0.747346 [Debug] dit_step35_xt: [2170, 64] first4: 0.499502 1.290683 -0.042988 0.075021 [DiT] Step 36/50 t=0.300 [Debug] dit_step36_vt: [2170, 64] first4: -0.596715 -0.603557 -0.184559 0.718959 [Debug] dit_step36_xt: [2170, 64] first4: 0.511436 1.302754 -0.039297 0.060642 [DiT] Step 37/50 t=0.280 [Debug] dit_step37_vt: [2170, 64] first4: -0.599306 -0.647603 -0.150218 0.665437 [Debug] dit_step37_xt: [2170, 64] first4: 0.523423 1.315706 -0.036293 0.047333 [DiT] Step 38/50 t=0.260 [Debug] dit_step38_vt: [2170, 64] first4: -0.563079 -0.775403 -0.181510 0.682864 [Debug] dit_step38_xt: [2170, 64] first4: 0.534684 1.331214 -0.032662 0.033676 [DiT] Step 39/50 t=0.240 [Debug] dit_step39_vt: [2170, 64] first4: -0.595561 -0.828018 -0.142625 0.595639 [Debug] dit_step39_xt: [2170, 64] first4: 0.546595 1.347775 -0.029810 0.021763 [DiT] Step 40/50 t=0.220 [Debug] dit_step40_vt: [2170, 64] first4: -0.568729 -0.858046 -0.057376 0.564957 [Debug] dit_step40_xt: [2170, 64] first4: 0.557970 1.364936 -0.028662 0.010464 [DiT] Step 41/50 t=0.200 [Debug] dit_step41_vt: [2170, 64] first4: -0.555885 -1.003272 -0.045344 0.519468 [Debug] dit_step41_xt: [2170, 64] first4: 0.569088 1.385001 -0.027755 0.000074 [DiT] Step 42/50 t=0.180 [Debug] dit_step42_vt: [2170, 64] first4: -0.491239 -1.006580 -0.013623 0.501674 [Debug] dit_step42_xt: [2170, 64] first4: 0.578912 1.405133 -0.027483 -0.009959 [DiT] Step 43/50 t=0.160 [Debug] dit_step43_vt: [2170, 64] first4: -0.477899 -1.063645 0.038636 0.435318 [Debug] dit_step43_xt: [2170, 64] first4: 0.588470 1.426406 -0.028256 -0.018665 [DiT] Step 44/50 t=0.140 [Debug] dit_step44_vt: [2170, 64] first4: -0.492690 -1.145716 0.083714 0.388190 [Debug] dit_step44_xt: [2170, 64] first4: 0.598324 1.449320 -0.029930 -0.026429 [DiT] Step 45/50 t=0.120 [Debug] dit_step45_vt: [2170, 64] first4: -0.480900 -1.190868 0.183933 0.344936 [Debug] dit_step45_xt: [2170, 64] first4: 0.607942 1.473137 -0.033609 -0.033328 [DiT] Step 46/50 t=0.100 [Debug] dit_step46_vt: [2170, 64] first4: -0.455232 -1.267096 0.216692 0.296702 [Debug] dit_step46_xt: [2170, 64] first4: 0.617047 1.498479 -0.037942 -0.039262 [DiT] Step 47/50 t=0.080 [Debug] dit_step47_vt: [2170, 64] first4: -0.424086 -1.270505 0.215407 0.249756 [Debug] dit_step47_xt: [2170, 64] first4: 0.625529 1.523889 -0.042251 -0.044257 [DiT] Step 48/50 t=0.060 [Debug] dit_step48_vt: [2170, 64] first4: -0.407557 -1.311973 0.188841 0.180014 [Debug] dit_step48_xt: [2170, 64] first4: 0.633680 1.550129 -0.046027 -0.047857 [DiT] Step 49/50 t=0.040 [Debug] dit_step49_vt: [2170, 64] first4: -0.417178 -1.341098 0.186318 0.184932 [Debug] dit_x0: [2170, 64] first4: 0.642023 1.576951 -0.049754 -0.051556 [DiT] Step 50/50 t=0.020 [DiT-Generate] Total: 136308.7 ms (136308.7 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.642023 1.576951 -0.049754 -0.051556 [Store] Unload DiT (1237.2 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: 704 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: 30674.8 ms [Debug] vae_audio: [2, 4166400] first4: -0.001585 -0.001109 -0.001387 -0.000992 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 441 ms (196.78x realtime), 32 threads [MP3] Wrote ggml-sft/request00.mp3 [Ace-Synth] All done 2026-07-12 08:48:17.273 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:174 - [initialize_service] Attempting to load model with attention implementation: sdpa 2026-07-12 08:48:19.772 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 08:48:19.772 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 08:48:19.772 | 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 08:48:19.775 | 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 08:48:19.780 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 08:48:19.786 | 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 08:48:19.788 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 08:48:19.788 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 08:48:19.788 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 08:48:19.788 | 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 08:48:19.788 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 08:48:19.788 | 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 08:48:19.788 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 08:48:19.792 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 08:48:19.800 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 08:48:19.800 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 08:48:19.806 | 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-Q6_K.gguf [GGML] Running acestep-v15-turbo-Q6_K.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 0.999627 detok_output 0.999927 context 0.999954 noise 1.000000 temb_t 0.999986 hidden_after_proj_in 0.999975 enc_after_cond_emb 0.999615 layer0_sa_output 0.999718 hidden_after_layer0 0.999825 hidden_after_layer6 0.999788 hidden_after_layer12 0.998912 hidden_after_layer18 0.995926 hidden_after_layer23 0.992285 dit_step0_vt 0.971194 dit_step0_xt 0.999936 dit_step1_vt 0.974424 dit_step1_xt 0.999799 dit_step2_vt 0.977923 dit_step2_xt 0.999471 dit_step3_vt 0.977600 dit_step3_xt 0.998717 dit_step4_vt 0.973239 dit_step4_xt 0.996917 dit_step5_vt 0.968741 dit_step5_xt 0.992644 dit_step6_vt 0.964555 dit_step6_xt 0.984241 dit_step7_vt 0.956646 dit_x0 0.971565 vae_audio 0.889756 vae_audio (STFT cosine) 0.967968 [Turbo] Error growth GGML vs Python stage cos max_err mean_err mean_A std_A mean_B std_B dit_step0_xt 0.999936 0.148925 0.007243 -0.002255 0.972904 -0.002342 0.972003 dit_step1_xt 0.999799 0.293564 0.012580 -0.005196 0.942625 -0.005313 0.941730 dit_step2_xt 0.999471 0.475913 0.019361 -0.009152 0.909045 -0.009311 0.908527 dit_step3_xt 0.998717 0.731060 0.028859 -0.014498 0.873512 -0.014577 0.873624 dit_step4_xt 0.996917 1.059091 0.042926 -0.021663 0.841485 -0.021660 0.841995 dit_step5_xt 0.992644 1.536603 0.064512 -0.031963 0.824626 -0.032109 0.824593 dit_step6_xt 0.984241 2.192945 0.097266 -0.046555 0.855647 -0.046482 0.855546 [SFT] steps=50, shift=1.0 | acestep-v15-sft-Q6_K.gguf [GGML] Running acestep-v15-sft-Q6_K.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-Q6_K.gguf: 830 tensors, data at offset 69088 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-turbo-Q6_K.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: 223 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-Q6_K.gguf: 830 tensors, data at offset 69088 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 141 tensors, 476.3 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L, CLS), text_proj, null_cond [Store] Load CondEnc: 310 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, 94.2 ms [Debug] enc_hidden: [238, 2048] first4: 0.687624 -0.020412 -0.050765 0.022580 [Store] Unload CondEnc (476.3 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-Q6_K.gguf: 830 tensors, data at offset 69088 [WeightCtx] Loaded 30 tensors, 82.2 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 48 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 355.8 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.151355 1.462444 0.326907 -0.627213 [Store] Unload FSQ-Detok (82.2 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: -0.151355 1.462444 0.326907 -0.627213 [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-Q6_K.gguf: 830 tensors, data at offset 69088 [DiT] Self-attn: Q+K+V fused [DiT] Cross-attn: Q+K+V fused [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 630 tensors, 3267.8 MB into backend [Load] DiT: 32 layers, H=2560, Nh=32/8, D=128 [Store] Load DiT: 2351 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2825 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [15360] first4: 0.018624 0.109874 0.060427 -0.073897 [Debug] temb: [2560] first4: 0.026456 -0.022590 -0.016414 0.047046 [Debug] temb_t: [2560] first4: 0.014595 -0.022043 -0.020712 0.048631 [Debug] temb_r: [2560] first4: 0.011861 -0.000548 0.004298 -0.001585 [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: 0.062874 -0.017498 0.137456 -0.111371 [Debug] temb_lin1_r: [2560] first4: -0.011992 0.015308 -0.017417 0.011656 [Debug] hidden_after_proj_in: [2560, 1085] first4: 0.343898 -0.584744 0.251996 -0.196074 [Debug] proj_in_input: [192, 2170] first4: -0.151355 1.462444 0.326907 -0.627213 [Debug] enc_after_cond_emb: [2560, 238] first4: 0.038852 0.672015 0.109741 0.865113 [Debug] layer0_sa_input: [2560, 1085] first4: 0.042658 -0.046178 0.089744 -0.136220 [Debug] layer0_q_after_rope: [128, 32] first4: -0.252196 -2.086671 0.334540 0.257373 [Debug] layer0_k_after_rope: [128, 8] first4: 0.045807 2.259551 0.599970 0.560670 [Debug] layer0_sa_output: [2560, 1085] first4: 1.651073 4.306114 -0.571291 5.315104 [Debug] layer0_attn_out: [4096, 1085] first4: 0.477567 -2.248265 -0.164023 -2.760866 [Debug] layer0_after_self_attn: [2560, 1085] first4: 0.477567 -2.248265 -0.164023 -2.760866 [Debug] layer0_after_cross_attn: [2560, 1085] first4: 0.348397 -2.015417 0.012216 -3.753975 [Debug] hidden_after_layer0: [2560, 1085] first4: 1.754470 -2.430678 236.301865 -3.720348 [Debug] hidden_after_layer6: [2560, 1085] first4: -6.289922 -3.056448 314.298523 -12.428476 [Debug] hidden_after_layer12: [2560, 1085] first4: -10.680946 29.674721 255.883896 31.333021 [Debug] hidden_after_layer18: [2560, 1085] first4: 41.366383 8.872893 274.152771 4.381433 [Debug] hidden_after_layer31: [2560, 1085] first4: -6.263082 -222.558502 -84.984062 109.535988 [Debug] dit_step0_vt: [2170, 64] first4: -0.823003 1.739476 0.831426 1.239563 [Debug] dit_step0_xt: [2170, 64] first4: 0.231745 2.077183 -0.209667 0.791312 [DiT] Step 1/8 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.955904 2.355939 0.680056 1.240894 [Debug] dit_step1_xt: [2170, 64] first4: 0.283885 1.948677 -0.246761 0.723627 [DiT] Step 2/8 t=0.955 [Debug] dit_step2_vt: [2170, 64] first4: -0.834294 1.447123 1.015135 0.973305 [Debug] dit_step2_xt: [2170, 64] first4: 0.339505 1.852202 -0.314437 0.658740 [DiT] Step 3/8 t=0.900 [Debug] dit_step3_vt: [2170, 64] first4: -0.307819 1.393339 0.973658 0.997936 [Debug] dit_step3_xt: [2170, 64] first4: 0.365157 1.736091 -0.395575 0.575579 [DiT] Step 4/8 t=0.833 [Debug] dit_step4_vt: [2170, 64] first4: -1.409967 2.543804 0.962544 0.399161 [Debug] dit_step4_xt: [2170, 64] first4: 0.516225 1.463540 -0.498705 0.532812 [DiT] Step 5/8 t=0.750 [Debug] dit_step5_vt: [2170, 64] first4: 0.483502 2.159396 1.241493 0.755564 [Debug] dit_step5_xt: [2170, 64] first4: 0.447153 1.155055 -0.676061 0.424874 [DiT] Step 6/8 t=0.643 [Debug] dit_step6_vt: [2170, 64] first4: 0.804386 1.983558 0.497095 0.907962 [Debug] dit_step6_xt: [2170, 64] first4: 0.286276 0.758343 -0.775480 0.243282 [DiT] Step 7/8 t=0.500 [Debug] dit_step7_vt: [2170, 64] first4: -1.054153 2.698039 1.519572 0.662501 [Debug] dit_x0: [2170, 64] first4: 0.602522 -0.051068 -1.231351 0.044531 [DiT] Step 8/8 t=0.300 [DiT-Generate] Total: 58471.5 ms (58471.5 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.602522 -0.051068 -1.231351 0.044531 [Store] Unload DiT (3267.8 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: 29369.6 ms [Debug] vae_audio: [2, 4166400] first4: 0.004724 0.007307 0.007057 0.006428 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 482 ms (180.09x realtime), 32 threads [MP3] Wrote ggml-xl-turbo/request00.mp3 [Ace-Synth] All done 2026-07-12 08:49:55.603 | 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 0.999627 detok_output 0.999927 context 0.999954 noise 1.000000 temb_t 0.999952 hidden_after_proj_in 0.999974 enc_after_cond_emb 0.999618 layer0_sa_output 0.999729 hidden_after_layer0 0.999852 hidden_after_layer6 0.999753 hidden_after_layer12 0.999301 hidden_after_layer18 0.998453 hidden_after_layer23 0.998713 dit_step0_vt 0.998620 dit_step0_xt 1.000000 dit_step5_vt 0.999111 dit_step5_xt 0.999974 dit_step10_vt 0.998487 dit_step10_xt 0.999910 dit_step15_vt 0.996913 dit_step15_xt 0.999760 dit_step20_vt 0.994477 dit_step20_xt 0.999389 dit_step25_vt 0.990223 dit_step25_xt 0.998666 dit_step30_vt 0.985153 dit_step30_xt 0.997413 dit_step35_vt 0.979729 dit_step35_xt 0.995755 dit_step40_vt 0.976227 dit_step40_xt 0.994029 dit_step45_vt 0.980117 dit_step45_xt 0.992782 dit_step49_vt 0.986572 dit_x0 0.992351 vae_audio 0.956163 vae_audio (STFT cosine) 0.980902 [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 0.019246 0.001510 -0.001664 0.978610 -0.001619 0.978872 dit_step5_xt 0.999974 0.083391 0.005131 -0.008398 0.885577 -0.008480 0.883811 dit_step10_xt 0.999910 0.102779 0.008217 -0.015053 0.801935 -0.015075 0.802324 dit_step15_xt 0.999760 0.138744 0.012261 -0.021632 0.731601 -0.021933 0.731304 dit_step20_xt 0.999389 0.222088 0.017929 -0.028220 0.679018 -0.028882 0.679066 dit_step25_xt 0.998666 0.372433 0.024859 -0.034858 0.648580 -0.035643 0.650780 dit_step30_xt 0.997413 0.567813 0.033802 -0.041514 0.643462 -0.042577 0.647107 dit_step35_xt 0.995755 0.830416 0.044304 -0.048165 0.664458 -0.049471 0.669256 dit_step40_xt 0.994029 1.090275 0.055972 -0.054834 0.709126 -0.056532 0.715783 dit_step45_xt 0.992782 1.324605 0.067045 -0.061583 0.773220 -0.063533 0.780575 [Xl-turbo] steps=8, shift=3.0 | acestep-v15-xl-turbo-Q6_K.gguf [GGML] Running acestep-v15-xl-turbo-Q6_K.gguf... [GGML] Done, 47 dump files [Python] Initializing acestep-v15-xl-turbo... Loading checkpoint shards: 0%| | 0/4 [00:00 1.0 (turbo does not use CFG). 2026-07-12 08:50:01.128 | INFO | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation... 2026-07-12 08:50:01.128 | INFO | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs... 2026-07-12 08:50:01.129 | 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 08:50:01.131 | 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 08:50:01.136 | INFO | acestep.core.generation.handler.conditioning_target:_prepare_target_latents_and_wavs:78 - [generate_music] Decoding audio codes for item 0... 2026-07-12 08:50:01.141 | 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 08:50:01.142 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - ====================================================================== 2026-07-12 08:50:01.142 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - πŸ” [DEBUG] DiT TEXT ENCODER INPUT (Inference) 2026-07-12 08:50:01.143 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ====================================================================== 2026-07-12 08:50:01.143 | 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 08:50:01.143 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 08:50:01.143 | 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 08:50:01.143 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 08:50:01.146 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 08:50:01.154 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 08:50:01.154 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 08:50:01.160 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)... 2026-07-12 08:50:01.167 | 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 08:50:01.729 | INFO | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:42 - [generate_music] Model generation completed. Decoding latents... 2026-07-12 08:50:01.730 | 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 08:50:01.730 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:65 - [generate_music] time_costs: {'encoder_time_cost': 0.006543159484863281, 'diffusion_time_cost': 0.5611147880554199, 'diffusion_per_step_time_cost': 0.07013934850692749, 'total_time_cost': 0.5676579475402832, 'offload_time_cost': 0.0} 2026-07-12 08:50:01.752 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:127 - [generate_music] Decoding latents with VAE... 2026-07-12 08:50:01.754 | DEBUG | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:136 - [generate_music] Before VAE decode: allocated=17.04GB, max=18.34GB 2026-07-12 08:50:01.755 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:154 - [generate_music] Effective free VRAM before VAE decode: 76.66 GB 2026-07-12 08:50:01.755 | 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 08:50:01.755 | DEBUG | acestep.core.generation.handler.memory_utils:_get_auto_decode_chunk_size:108 - [_get_auto_decode_chunk_size] Effective free VRAM: 76.66 GB 2026-07-12 08:50:01.755 | DEBUG | acestep.core.generation.handler.memory_utils:_should_offload_wav_to_cpu:131 - [_should_offload_wav_to_cpu] Effective free VRAM: 76.66 GB 2026-07-12 08:50:01.755 | 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 08:50:02.029 | DEBUG | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:193 - [generate_music] After VAE decode: allocated=17.21GB, max=18.50GB 2026-07-12 08:50:02.229 | 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 08:50:02.233 | 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-Q6_K.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-Q6_K.gguf: 830 tensors, data at offset 69056 [GGUF] /mnt/workspace/git/acestep.cpp/models/acestep-v15-xl-sft-Q6_K.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: 222 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-Q6_K.gguf: 830 tensors, data at offset 69056 [Load] LyricEncoder: 8L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [Load] TimbreEncoder: 4L [Qwen3] Attn: Q+K+V fused [Qwen3] MLP: gate+up fused [WeightCtx] Loaded 141 tensors, 476.3 MB into backend [Load] CondEncoder: lyric(8L), timbre(4L, CLS), text_proj, null_cond [Store] Load CondEnc: 296 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, 94.0 ms [Debug] enc_hidden: [238, 2048] first4: 0.687624 -0.020412 -0.050765 0.022580 [Store] Unload CondEnc (476.3 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-Q6_K.gguf: 830 tensors, data at offset 69056 [WeightCtx] Loaded 30 tensors, 82.2 MB into backend [Load] Detokenizer: FSQ(6->2048) + 2L encoder(S=5, 2048->64) [Store] Load FSQ-Detok: 57 ms [Context] Decoded: 434 codes -> 2170 frames (86.8s @ 25Hz) [Build-Context Batch0] Detokenizer: 351.7 ms, 434 codes [Debug] detok_output: [2170, 64] first4: -0.151355 1.462444 0.326907 -0.627213 [Store] Unload FSQ-Detok (82.2 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: -0.151355 1.462444 0.326907 -0.627213 [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-Q6_K.gguf: 830 tensors, data at offset 69056 [DiT] Self-attn: Q+K+V fused [DiT] Cross-attn: Q+K+V fused [DiT] MLP: gate+up fused [Load] null_condition_emb found (CFG available) [WeightCtx] Loaded 630 tensors, 3267.8 MB into backend [Load] DiT: 32 layers, H=2560, Nh=32/8, D=128 [Store] Load DiT: 2257 ms [DiT] Batch N=1, T=2170, S=1085, enc_S=238 [DiT] Graph: 2825 nodes [DiT] Solver: ODE Euler (1 NFE/step, order 1) [Debug] tproj: [15360] first4: 0.009506 0.101242 0.073779 -0.034931 [Debug] temb: [2560] first4: 0.009704 -0.007647 -0.006160 0.004419 [Debug] temb_t: [2560] first4: 0.008233 -0.007846 -0.006666 0.003417 [Debug] temb_r: [2560] first4: 0.001471 0.000199 0.000506 0.001001 [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: 0.034102 -0.082811 0.088383 -0.064701 [Debug] temb_lin1_r: [2560] first4: 0.009306 -0.004837 -0.002965 -0.011076 [Debug] hidden_after_proj_in: [2560, 1085] first4: 0.333331 -0.500216 0.123159 -0.219648 [Debug] proj_in_input: [192, 2170] first4: -0.151355 1.462444 0.326907 -0.627213 [Debug] enc_after_cond_emb: [2560, 238] first4: 0.046758 0.645454 0.121823 0.862796 [Debug] layer0_sa_input: [2560, 1085] first4: 0.033760 -0.024849 0.099830 -0.102151 [Debug] layer0_q_after_rope: [128, 32] first4: -0.262700 -2.150678 0.318646 0.004803 [Debug] layer0_k_after_rope: [128, 8] first4: 0.759861 2.969560 1.271230 1.949076 [Debug] layer0_sa_output: [2560, 1085] first4: 1.965966 4.395340 -0.761963 7.744899 [Debug] layer0_attn_out: [4096, 1085] first4: 0.463727 -2.179160 -0.440477 -4.073095 [Debug] layer0_after_self_attn: [2560, 1085] first4: 0.463727 -2.179160 -0.440477 -4.073095 [Debug] layer0_after_cross_attn: [2560, 1085] first4: 0.299487 -1.915637 -0.360635 -4.138309 [Debug] hidden_after_layer0: [2560, 1085] first4: -1.565226 -1.272830 243.935760 -4.055056 [Debug] hidden_after_layer6: [2560, 1085] first4: -7.243199 3.910677 305.820038 -21.876902 [Debug] hidden_after_layer12: [2560, 1085] first4: -22.202169 38.657459 221.398972 15.539539 [Debug] hidden_after_layer18: [2560, 1085] first4: 10.920046 -13.138327 226.405396 19.980648 [Debug] hidden_after_layer31: [2560, 1085] first4: 65.760437 -106.984703 13.166077 90.631363 [Debug] dit_step0_vt: [2170, 64] first4: -0.312118 2.165119 0.054935 1.683498 [Debug] dit_step0_xt: [2170, 64] first4: 0.200578 2.112948 -0.172974 0.813986 [DiT] Step 1/50 t=1.000 [Debug] dit_step1_vt: [2170, 64] first4: -0.341468 2.139199 0.102816 1.531485 [Debug] dit_step1_xt: [2170, 64] first4: 0.207408 2.070164 -0.175030 0.783357 [DiT] Step 2/50 t=0.980 [Debug] dit_step2_vt: [2170, 64] first4: -0.314436 2.139104 0.077881 1.559264 [Debug] dit_step2_xt: [2170, 64] first4: 0.213696 2.027382 -0.176588 0.752171 [DiT] Step 3/50 t=0.960 [Debug] dit_step3_vt: [2170, 64] first4: -0.257257 2.114859 0.061832 1.547791 [Debug] dit_step3_xt: [2170, 64] first4: 0.218842 1.985085 -0.177824 0.721215 [DiT] Step 4/50 t=0.940 [Debug] dit_step4_vt: [2170, 64] first4: -0.240043 2.043654 0.079748 1.570388 [Debug] dit_step4_xt: [2170, 64] first4: 0.223642 1.944211 -0.179419 0.689808 [DiT] Step 5/50 t=0.920 [Debug] dit_step5_vt: [2170, 64] first4: -0.252565 2.031645 0.089615 1.568982 [Debug] dit_step5_xt: [2170, 64] first4: 0.228694 1.903579 -0.181212 0.658428 [DiT] Step 6/50 t=0.900 [Debug] dit_step6_vt: [2170, 64] first4: -0.248046 2.005031 0.090932 1.578172 [Debug] dit_step6_xt: [2170, 64] first4: 0.233655 1.863478 -0.183030 0.626865 [DiT] Step 7/50 t=0.880 [Debug] dit_step7_vt: [2170, 64] first4: -0.241430 1.963342 0.153826 1.580950 [Debug] dit_step7_xt: [2170, 64] first4: 0.238483 1.824211 -0.186107 0.595246 [DiT] Step 8/50 t=0.860 [Debug] dit_step8_vt: [2170, 64] first4: -0.247221 1.924948 0.171996 1.582265 [Debug] dit_step8_xt: [2170, 64] first4: 0.243428 1.785712 -0.189547 0.563600 [DiT] Step 9/50 t=0.840 [Debug] dit_step9_vt: [2170, 64] first4: -0.279197 1.856230 0.152352 1.580291 [Debug] dit_step9_xt: [2170, 64] first4: 0.249012 1.748588 -0.192594 0.531995 [DiT] Step 10/50 t=0.820 [Debug] dit_step10_vt: [2170, 64] first4: -0.285609 1.815982 0.112451 1.563257 [Debug] dit_step10_xt: [2170, 64] first4: 0.254724 1.712268 -0.194843 0.500729 [DiT] Step 11/50 t=0.800 [Debug] dit_step11_vt: [2170, 64] first4: -0.279647 1.761330 0.091275 1.553255 [Debug] dit_step11_xt: [2170, 64] first4: 0.260317 1.677041 -0.196668 0.469664 [DiT] Step 12/50 t=0.780 [Debug] dit_step12_vt: [2170, 64] first4: -0.308650 1.705133 0.089894 1.521542 [Debug] dit_step12_xt: [2170, 64] first4: 0.266490 1.642939 -0.198466 0.439233 [DiT] Step 13/50 t=0.760 [Debug] dit_step13_vt: [2170, 64] first4: -0.266486 1.657972 0.071046 1.512328 [Debug] dit_step13_xt: [2170, 64] first4: 0.271819 1.609779 -0.199887 0.408987 [DiT] Step 14/50 t=0.740 [Debug] dit_step14_vt: [2170, 64] first4: -0.282828 1.605561 0.070508 1.513308 [Debug] dit_step14_xt: [2170, 64] first4: 0.277476 1.577668 -0.201297 0.378721 [DiT] Step 15/50 t=0.720 [Debug] dit_step15_vt: [2170, 64] first4: -0.261520 1.545930 0.067757 1.525308 [Debug] dit_step15_xt: [2170, 64] first4: 0.282706 1.546749 -0.202652 0.348215 [DiT] Step 16/50 t=0.700 [Debug] dit_step16_vt: [2170, 64] first4: -0.210834 1.485118 0.022251 1.500093 [Debug] dit_step16_xt: [2170, 64] first4: 0.286923 1.517047 -0.203097 0.318213 [DiT] Step 17/50 t=0.680 [Debug] dit_step17_vt: [2170, 64] first4: -0.218593 1.458751 0.017055 1.487127 [Debug] dit_step17_xt: [2170, 64] first4: 0.291295 1.487872 -0.203438 0.288470 [DiT] Step 18/50 t=0.660 [Debug] dit_step18_vt: [2170, 64] first4: -0.172251 1.396866 -0.006375 1.506454 [Debug] dit_step18_xt: [2170, 64] first4: 0.294740 1.459935 -0.203311 0.258341 [DiT] Step 19/50 t=0.640 [Debug] dit_step19_vt: [2170, 64] first4: -0.148795 1.341083 0.008529 1.506899 [Debug] dit_step19_xt: [2170, 64] first4: 0.297716 1.433113 -0.203481 0.228203 [DiT] Step 20/50 t=0.620 [Debug] dit_step20_vt: [2170, 64] first4: -0.116635 1.335072 -0.041037 1.495311 [Debug] dit_step20_xt: [2170, 64] first4: 0.300049 1.406412 -0.202661 0.198297 [DiT] Step 21/50 t=0.600 [Debug] dit_step21_vt: [2170, 64] first4: -0.070199 1.274337 -0.036713 1.474424 [Debug] dit_step21_xt: [2170, 64] first4: 0.301453 1.380925 -0.201926 0.168808 [DiT] Step 22/50 t=0.580 [Debug] dit_step22_vt: [2170, 64] first4: -0.067549 1.204090 -0.033695 1.443180 [Debug] dit_step22_xt: [2170, 64] first4: 0.302804 1.356843 -0.201253 0.139945 [DiT] Step 23/50 t=0.560 [Debug] dit_step23_vt: [2170, 64] first4: -0.066516 1.160445 -0.057857 1.447303 [Debug] dit_step23_xt: [2170, 64] first4: 0.304134 1.333634 -0.200095 0.110999 [DiT] Step 24/50 t=0.540 [Debug] dit_step24_vt: [2170, 64] first4: -0.030811 1.112594 -0.066080 1.416779 [Debug] dit_step24_xt: [2170, 64] first4: 0.304750 1.311382 -0.198774 0.082663 [DiT] Step 25/50 t=0.520 [Debug] dit_step25_vt: [2170, 64] first4: -0.026273 1.073788 -0.083797 1.380007 [Debug] dit_step25_xt: [2170, 64] first4: 0.305276 1.289906 -0.197098 0.055063 [DiT] Step 26/50 t=0.500 [Debug] dit_step26_vt: [2170, 64] first4: -0.034369 0.993524 -0.086148 1.376915 [Debug] dit_step26_xt: [2170, 64] first4: 0.305963 1.270036 -0.195375 0.027525 [DiT] Step 27/50 t=0.480 [Debug] dit_step27_vt: [2170, 64] first4: -0.096016 0.943645 -0.078216 1.333935 [Debug] dit_step27_xt: [2170, 64] first4: 0.307883 1.251163 -0.193811 0.000846 [DiT] Step 28/50 t=0.460 [Debug] dit_step28_vt: [2170, 64] first4: -0.073810 0.863317 -0.058145 1.327243 [Debug] dit_step28_xt: [2170, 64] first4: 0.309359 1.233897 -0.192648 -0.025699 [DiT] Step 29/50 t=0.440 [Debug] dit_step29_vt: [2170, 64] first4: -0.076400 0.842622 -0.111944 1.259983 [Debug] dit_step29_xt: [2170, 64] first4: 0.310887 1.217044 -0.190409 -0.050899 [DiT] Step 30/50 t=0.420 [Debug] dit_step30_vt: [2170, 64] first4: -0.064174 0.703017 -0.095823 1.252907 [Debug] dit_step30_xt: [2170, 64] first4: 0.312171 1.202984 -0.188492 -0.075957 [DiT] Step 31/50 t=0.400 [Debug] dit_step31_vt: [2170, 64] first4: -0.127586 0.679904 -0.082500 1.233218 [Debug] dit_step31_xt: [2170, 64] first4: 0.314723 1.189386 -0.186842 -0.100621 [DiT] Step 32/50 t=0.380 [Debug] dit_step32_vt: [2170, 64] first4: -0.104836 0.591701 -0.109211 1.227324 [Debug] dit_step32_xt: [2170, 64] first4: 0.316819 1.177552 -0.184658 -0.125168 [DiT] Step 33/50 t=0.360 [Debug] dit_step33_vt: [2170, 64] first4: -0.128380 0.469188 -0.111351 1.226147 [Debug] dit_step33_xt: [2170, 64] first4: 0.319387 1.168168 -0.182431 -0.149690 [DiT] Step 34/50 t=0.340 [Debug] dit_step34_vt: [2170, 64] first4: -0.136474 0.392480 -0.105841 1.165859 [Debug] dit_step34_xt: [2170, 64] first4: 0.322116 1.160318 -0.180314 -0.173008 [DiT] Step 35/50 t=0.320 [Debug] dit_step35_vt: [2170, 64] first4: -0.153584 0.274831 -0.055779 1.118689 [Debug] dit_step35_xt: [2170, 64] first4: 0.325188 1.154822 -0.179199 -0.195381 [DiT] Step 36/50 t=0.300 [Debug] dit_step36_vt: [2170, 64] first4: -0.127021 0.222478 -0.078089 1.036688 [Debug] dit_step36_xt: [2170, 64] first4: 0.327729 1.150372 -0.177637 -0.216115 [DiT] Step 37/50 t=0.280 [Debug] dit_step37_vt: [2170, 64] first4: -0.108085 0.088709 -0.098974 1.055198 [Debug] dit_step37_xt: [2170, 64] first4: 0.329890 1.148598 -0.175658 -0.237219 [DiT] Step 38/50 t=0.260 [Debug] dit_step38_vt: [2170, 64] first4: -0.149936 -0.066453 -0.063798 0.999242 [Debug] dit_step38_xt: [2170, 64] first4: 0.332889 1.149927 -0.174382 -0.257204 [DiT] Step 39/50 t=0.240 [Debug] dit_step39_vt: [2170, 64] first4: -0.209685 -0.138829 -0.071719 0.967968 [Debug] dit_step39_xt: [2170, 64] first4: 0.337083 1.152704 -0.172947 -0.276563 [DiT] Step 40/50 t=0.220 [Debug] dit_step40_vt: [2170, 64] first4: -0.234501 -0.233907 -0.014645 0.922591 [Debug] dit_step40_xt: [2170, 64] first4: 0.341773 1.157382 -0.172654 -0.295015 [DiT] Step 41/50 t=0.200 [Debug] dit_step41_vt: [2170, 64] first4: -0.277664 -0.383506 0.025094 0.858579 [Debug] dit_step41_xt: [2170, 64] first4: 0.347326 1.165052 -0.173156 -0.312187 [DiT] Step 42/50 t=0.180 [Debug] dit_step42_vt: [2170, 64] first4: -0.296430 -0.448398 0.044245 0.787135 [Debug] dit_step42_xt: [2170, 64] first4: 0.353254 1.174020 -0.174041 -0.327929 [DiT] Step 43/50 t=0.160 [Debug] dit_step43_vt: [2170, 64] first4: -0.336976 -0.560755 -0.002685 0.785448 [Debug] dit_step43_xt: [2170, 64] first4: 0.359994 1.185235 -0.173987 -0.343638 [DiT] Step 44/50 t=0.140 [Debug] dit_step44_vt: [2170, 64] first4: -0.331569 -0.644150 0.082753 0.729164 [Debug] dit_step44_xt: [2170, 64] first4: 0.366625 1.198118 -0.175642 -0.358222 [DiT] Step 45/50 t=0.120 [Debug] dit_step45_vt: [2170, 64] first4: -0.402313 -0.697011 0.126558 0.671973 [Debug] dit_step45_xt: [2170, 64] first4: 0.374672 1.212058 -0.178174 -0.371661 [DiT] Step 46/50 t=0.100 [Debug] dit_step46_vt: [2170, 64] first4: -0.398635 -0.780858 0.184885 0.647651 [Debug] dit_step46_xt: [2170, 64] first4: 0.382644 1.227675 -0.181871 -0.384614 [DiT] Step 47/50 t=0.080 [Debug] dit_step47_vt: [2170, 64] first4: -0.459759 -0.854349 0.220030 0.590230 [Debug] dit_step47_xt: [2170, 64] first4: 0.391840 1.244762 -0.186272 -0.396419 [DiT] Step 48/50 t=0.060 [Debug] dit_step48_vt: [2170, 64] first4: -0.508089 -0.930213 0.252105 0.615575 [Debug] dit_step48_xt: [2170, 64] first4: 0.402001 1.263367 -0.191314 -0.408730 [DiT] Step 49/50 t=0.040 [Debug] dit_step49_vt: [2170, 64] first4: -0.545444 -0.912987 0.206528 0.629950 [Debug] dit_x0: [2170, 64] first4: 0.412910 1.281626 -0.195445 -0.421329 [DiT] Step 50/50 t=0.020 [DiT-Generate] Total: 370395.4 ms (370395.4 ms/sample) [Debug] dit_output: [2170, 64] first4: 0.412910 1.281626 -0.195445 -0.421329 [Store] Unload DiT (3267.8 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: 713 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: 27935.9 ms [Debug] vae_audio: [2, 4166400] first4: -0.001409 -0.000689 -0.000819 -0.000320 [Store] Unload VAE-Dec (161.1 MB) [MP3] Encoding 86.8s @ 128 kbps, 48000 Hz stereo [MP3] 1388928 bytes (12.0:1), 458 ms (189.61x realtime), 32 threads [MP3] Wrote ggml-xl-sft/request00.mp3 [Ace-Synth] All done 2026-07-12 08:56:46.145 | 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 0.999359 detok_output 0.999927 context 0.999954 noise 1.000000 temb_t 0.999968 hidden_after_proj_in 0.999961 enc_after_cond_emb 0.999393 layer0_sa_output 0.999156 hidden_after_layer0 0.999317 hidden_after_layer6 0.999718 hidden_after_layer12 0.995710 hidden_after_layer18 0.995794 hidden_after_layer31 0.988118 dit_step0_vt 0.911489 dit_step0_xt 0.999841 dit_step1_vt 0.927722 dit_step1_xt 0.999523 dit_step2_vt 0.928489 dit_step2_xt 0.998751 dit_step3_vt 0.922798 dit_step3_xt 0.996870 dit_step4_vt 0.920194 dit_step4_xt 0.992460 dit_step5_vt 0.911076 dit_step5_xt 0.981699 dit_step6_vt 0.903942 dit_step6_xt 0.960322 dit_step7_vt 0.884130 dit_x0 0.925859 vae_audio 0.726333 vae_audio (STFT cosine) 0.922192 [Xl-turbo] Error growth GGML vs Python stage cos max_err mean_err mean_A std_A mean_B std_B dit_step0_xt 0.999841 0.244726 0.012571 -0.002986 0.978462 -0.002721 0.976534 dit_step1_xt 0.999523 0.311116 0.021429 -0.005966 0.952183 -0.005567 0.949004 dit_step2_xt 0.998751 0.546949 0.033195 -0.009759 0.923676 -0.009330 0.918931 dit_step3_xt 0.996870 0.812528 0.050016 -0.015289 0.893083 -0.014418 0.887241 dit_step4_xt 0.992460 1.272408 0.074385 -0.022973 0.863798 -0.021453 0.857796 dit_step5_xt 0.981699 2.305293 0.113178 -0.034211 0.847663 -0.032240 0.840033 dit_step6_xt 0.960322 3.872262 0.172187 -0.051348 0.873400 -0.049194 0.863964 [Xl-sft] steps=50, shift=1.0 | acestep-v15-xl-sft-Q6_K.gguf [GGML] Running acestep-v15-xl-sft-Q6_K.gguf... [GGML] Done, 131 dump files [Python] Initializing acestep-v15-xl-sft... Loading checkpoint shards: 0%| | 0/4 [00:00 2026-07-12 08:56:48.554 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ====================================================================== 2026-07-12 08:56:48.554 | 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 08:56:48.554 | INFO | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ====================================================================== 2026-07-12 08:56:48.558 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings... 2026-07-12 08:56:48.566 | INFO | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings... 2026-07-12 08:56:48.566 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) 2026-07-12 08:56:48.572 | 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