enne2/qwentts.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

logs

Browse Source
This commit is contained in:
Pascal
2026-07-05 07:47:07 +02:00
parent 415ef56330
commit bcac46352e
12 changed files with 170 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/clone-CPU-BF16.log
+10 -10
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -33,7 +33,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Audio-Resample] Done: 380672 -> 414337 samples [Audio-Resample] Done: 380672 -> 414337 samples
[WeightCtx] Loaded 76 tensors, 34.9 MB into backend [WeightCtx] Loaded 76 tensors, 34.9 MB into backend
[SpeakerEncoder] Loaded: enc_dim=2048 sr=24000 mel_dim=128 hidden=512 mfa=1536 asp_attn=128 se=128 scale=8 [SpeakerEncoder] Loaded: enc_dim=2048 sr=24000 mel_dim=128 hidden=512 mfa=1536 asp_attn=128 se=128 scale=8
[Pipeline] Speaker encoder lazy loaded in 3 ms [Pipeline] Speaker encoder lazy loaded in 6 ms
[Debug] mel-spk: [1618, 128] first4: -6.330339 -6.170074 -6.011195 -6.243161 [Debug] mel-spk: [1618, 128] first4: -6.330339 -6.170074 -6.011195 -6.243161
[Debug] mel-hann: [1024] first4: 0.000000 0.000009 0.000038 0.000085 [Debug] mel-hann: [1024] first4: 0.000000 0.000009 0.000038 0.000085
[Debug] mel-basis: [128, 513] first4: 0.000000 0.033550 0.008569 0.000000 [Debug] mel-basis: [128, 513] first4: 0.000000 0.033550 0.008569 0.000000
@@ -51,7 +51,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB [EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB
[WeightCtx] Loaded 20 tensors, 34.0 MB into backend [WeightCtx] Loaded 20 tensors, 34.0 MB into backend
[EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB [EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB
[Pipeline] Codec encoder lazy loaded in 41 ms [Pipeline] Codec encoder lazy loaded in 54 ms
[Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340 [Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340
[Debug] seanet-out: [430, 512] first4: -0.112500 13.760122 -0.329032 2.993861 [Debug] seanet-out: [430, 512] first4: -0.112500 13.760122 -0.329032 2.993861
[Debug] enc-transformer-out: [430, 512] first4: 0.526661 3.208130 -0.164395 0.605249 [Debug] enc-transformer-out: [430, 512] first4: 0.526661 3.208130 -0.164395 0.605249
@@ -122,14 +122,14 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Pipeline] Generation done : 64 frames [Pipeline] Generation done : 64 frames
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000
[Debug] output-audio: [122880] first4: 0.000529 0.000353 -0.000865 -0.000453 [Debug] output-audio: [122880] first4: 0.000529 0.000353 -0.000865 -0.000453
[Perf] PromptBuild 2.9 ms [Perf] PromptBuild 2.8 ms
[Perf] Prefill 389.4 ms (T_ctx prefill) [Perf] Prefill 380.0 ms (T_ctx prefill)
[Perf] TTFA 417.5 ms (first frame codes) [Perf] TTFA 408.1 ms (first frame codes)
[Perf] TalkerDecode 2918.4 ms (64 frames, 45.60 ms/frame) [Perf] TalkerDecode 2920.2 ms (64 frames, 45.63 ms/frame)
[Perf] CodePredictor 1492.6 ms (23.32 ms/frame) [Perf] CodePredictor 1452.0 ms (22.69 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 974.0 ms [Perf] CodecDecode 1021.6 ms
[Perf] Total 5778.7 ms (64 frames, 68.92 ms/frame AR, audio 5.12 s, RTF 1.129) [Perf] Total 5778.3 ms (64 frames, 68.32 ms/frame AR, audio 5.12 s, RTF 1.129)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-CPU-F32.log
+10 -10
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -33,7 +33,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Audio-Resample] Done: 380672 -> 414337 samples [Audio-Resample] Done: 380672 -> 414337 samples
[WeightCtx] Loaded 76 tensors, 45.8 MB into backend [WeightCtx] Loaded 76 tensors, 45.8 MB into backend
[SpeakerEncoder] Loaded: enc_dim=2048 sr=24000 mel_dim=128 hidden=512 mfa=1536 asp_attn=128 se=128 scale=8 [SpeakerEncoder] Loaded: enc_dim=2048 sr=24000 mel_dim=128 hidden=512 mfa=1536 asp_attn=128 se=128 scale=8
[Pipeline] Speaker encoder lazy loaded in 5 ms [Pipeline] Speaker encoder lazy loaded in 6 ms
[Debug] mel-spk: [1618, 128] first4: -6.330339 -6.170074 -6.011195 -6.243161 [Debug] mel-spk: [1618, 128] first4: -6.330339 -6.170074 -6.011195 -6.243161
[Debug] mel-hann: [1024] first4: 0.000000 0.000009 0.000038 0.000085 [Debug] mel-hann: [1024] first4: 0.000000 0.000009 0.000038 0.000085
[Debug] mel-basis: [128, 513] first4: 0.000000 0.033550 0.008569 0.000000 [Debug] mel-basis: [128, 513] first4: 0.000000 0.033550 0.008569 0.000000
@@ -51,7 +51,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB [EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB
[WeightCtx] Loaded 20 tensors, 34.0 MB into backend [WeightCtx] Loaded 20 tensors, 34.0 MB into backend
[EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB [EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB
[Pipeline] Codec encoder lazy loaded in 35 ms [Pipeline] Codec encoder lazy loaded in 34 ms
[Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340 [Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340
[Debug] seanet-out: [430, 512] first4: -0.120292 13.742489 -0.348104 3.009387 [Debug] seanet-out: [430, 512] first4: -0.120292 13.742489 -0.348104 3.009387
[Debug] enc-transformer-out: [430, 512] first4: 0.526076 3.125370 -0.189241 0.630764 [Debug] enc-transformer-out: [430, 512] first4: 0.526076 3.125370 -0.189241 0.630764
@@ -122,14 +122,14 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Pipeline] Generation done : 64 frames [Pipeline] Generation done : 64 frames
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000
[Debug] output-audio: [122880] first4: 0.000450 0.000327 -0.000890 -0.000492 [Debug] output-audio: [122880] first4: 0.000450 0.000327 -0.000890 -0.000492
[Perf] PromptBuild 5.0 ms [Perf] PromptBuild 3.8 ms
[Perf] Prefill 695.5 ms (T_ctx prefill) [Perf] Prefill 623.1 ms (T_ctx prefill)
[Perf] TTFA 766.0 ms (first frame codes) [Perf] TTFA 690.7 ms (first frame codes)
[Perf] TalkerDecode 5506.9 ms (64 frames, 86.04 ms/frame) [Perf] TalkerDecode 5586.7 ms (64 frames, 87.29 ms/frame)
[Perf] CodePredictor 3926.2 ms (61.35 ms/frame) [Perf] CodePredictor 3937.5 ms (61.52 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 1029.6 ms [Perf] CodecDecode 1012.2 ms
[Perf] Total 11164.8 ms (64 frames, 147.39 ms/frame AR, audio 5.12 s, RTF 2.181) [Perf] Total 11164.9 ms (64 frames, 148.82 ms/frame AR, audio 5.12 s, RTF 2.181)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-CPU-Q4_K_M.log
+8 -8
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -51,7 +51,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB [EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB
[WeightCtx] Loaded 20 tensors, 34.0 MB into backend [WeightCtx] Loaded 20 tensors, 34.0 MB into backend
[EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB [EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB
[Pipeline] Codec encoder lazy loaded in 7 ms [Pipeline] Codec encoder lazy loaded in 8 ms
[Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340 [Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340
[Debug] seanet-out: [430, 512] first4: -0.120292 13.742489 -0.348104 3.009387 [Debug] seanet-out: [430, 512] first4: -0.120292 13.742489 -0.348104 3.009387
[Debug] enc-transformer-out: [430, 512] first4: 0.867046 3.016766 0.059672 0.395116 [Debug] enc-transformer-out: [430, 512] first4: 0.867046 3.016766 0.059672 0.395116
@@ -123,13 +123,13 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 417.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 417.000000
[Debug] output-audio: [122880] first4: -0.000160 -0.000284 -0.001051 -0.000894 [Debug] output-audio: [122880] first4: -0.000160 -0.000284 -0.001051 -0.000894
[Perf] PromptBuild 2.8 ms [Perf] PromptBuild 2.8 ms
[Perf] Prefill 417.7 ms (T_ctx prefill) [Perf] Prefill 414.8 ms (T_ctx prefill)
[Perf] TTFA 428.0 ms (first frame codes) [Perf] TTFA 425.6 ms (first frame codes)
[Perf] TalkerDecode 973.2 ms (64 frames, 15.21 ms/frame) [Perf] TalkerDecode 990.4 ms (64 frames, 15.48 ms/frame)
[Perf] CodePredictor 407.1 ms (6.36 ms/frame) [Perf] CodePredictor 415.2 ms (6.49 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 991.3 ms [Perf] CodecDecode 1031.5 ms
[Perf] Total 2793.5 ms (64 frames, 21.57 ms/frame AR, audio 5.12 s, RTF 0.546) [Perf] Total 2856.3 ms (64 frames, 21.96 ms/frame AR, audio 5.12 s, RTF 0.558)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-CPU-Q8_0.log
+9 -9
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -51,7 +51,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB [EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB
[WeightCtx] Loaded 20 tensors, 34.0 MB into backend [WeightCtx] Loaded 20 tensors, 34.0 MB into backend
[EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB [EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB
[Pipeline] Codec encoder lazy loaded in 8 ms [Pipeline] Codec encoder lazy loaded in 9 ms
[Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340 [Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340
[Debug] seanet-out: [430, 512] first4: -0.120292 13.742489 -0.348104 3.009387 [Debug] seanet-out: [430, 512] first4: -0.120292 13.742489 -0.348104 3.009387
[Debug] enc-transformer-out: [430, 512] first4: 0.716872 2.959070 -0.221450 0.852651 [Debug] enc-transformer-out: [430, 512] first4: 0.716872 2.959070 -0.221450 0.852651
@@ -122,14 +122,14 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Pipeline] Generation done : 64 frames [Pipeline] Generation done : 64 frames
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000
[Debug] output-audio: [122880] first4: 0.000527 0.000324 -0.000983 -0.000676 [Debug] output-audio: [122880] first4: 0.000527 0.000324 -0.000983 -0.000676
[Perf] PromptBuild 2.8 ms [Perf] PromptBuild 3.3 ms
[Perf] Prefill 619.0 ms (T_ctx prefill) [Perf] Prefill 615.3 ms (T_ctx prefill)
[Perf] TTFA 634.3 ms (first frame codes) [Perf] TTFA 631.6 ms (first frame codes)
[Perf] TalkerDecode 1668.8 ms (64 frames, 26.07 ms/frame) [Perf] TalkerDecode 1675.4 ms (64 frames, 26.18 ms/frame)
[Perf] CodePredictor 651.2 ms (10.17 ms/frame) [Perf] CodePredictor 650.8 ms (10.17 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 987.3 ms [Perf] CodecDecode 993.5 ms
[Perf] Total 3930.5 ms (64 frames, 36.25 ms/frame AR, audio 5.12 s, RTF 0.768) [Perf] Total 3948.8 ms (64 frames, 36.35 ms/frame AR, audio 5.12 s, RTF 0.771)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-CUDA0-BF16.log
+26 -9
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -33,7 +33,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Audio-Resample] Done: 380672 -> 414337 samples [Audio-Resample] Done: 380672 -> 414337 samples
[WeightCtx] Loaded 76 tensors, 34.9 MB into backend [WeightCtx] Loaded 76 tensors, 34.9 MB into backend
[SpeakerEncoder] Loaded: enc_dim=2048 sr=24000 mel_dim=128 hidden=512 mfa=1536 asp_attn=128 se=128 scale=8 [SpeakerEncoder] Loaded: enc_dim=2048 sr=24000 mel_dim=128 hidden=512 mfa=1536 asp_attn=128 se=128 scale=8
[Pipeline] Speaker encoder lazy loaded in 22 ms [Pipeline] Speaker encoder lazy loaded in 3 ms
[Debug] mel-spk: [1618, 128] first4: -6.330339 -6.170074 -6.011195 -6.243161 [Debug] mel-spk: [1618, 128] first4: -6.330339 -6.170074 -6.011195 -6.243161
[Debug] mel-hann: [1024] first4: 0.000000 0.000009 0.000038 0.000085 [Debug] mel-hann: [1024] first4: 0.000000 0.000009 0.000038 0.000085
[Debug] mel-basis: [128, 513] first4: 0.000000 0.033550 0.008569 0.000000 [Debug] mel-basis: [128, 513] first4: 0.000000 0.033550 0.008569 0.000000
@@ -51,7 +51,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB [EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB
[WeightCtx] Loaded 20 tensors, 34.0 MB into backend [WeightCtx] Loaded 20 tensors, 34.0 MB into backend
[EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB [EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB
[Pipeline] Codec encoder lazy loaded in 91 ms [Pipeline] Codec encoder lazy loaded in 63 ms
[Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340 [Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340
[Debug] seanet-out: [430, 512] first4: -0.111631 13.770183 -0.302467 2.984188 [Debug] seanet-out: [430, 512] first4: -0.111631 13.770183 -0.302467 2.984188
[Debug] enc-transformer-out: [430, 512] first4: 0.531195 3.238480 -0.146394 0.612285 [Debug] enc-transformer-out: [430, 512] first4: 0.531195 3.238480 -0.146394 0.612285
@@ -98,24 +98,41 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Sample] step=1 c0=1902 u=-1.0000000000 subseq=16 [Sample] step=1 c0=1902 u=-1.0000000000 subseq=16
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=0 c=1924 u=-1.0000000000 subseq=17 [Sample-CP] g=0 c=1924 u=-1.0000000000 subseq=17
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=1 c=2025 u=-1.0000000000 subseq=18 [Sample-CP] g=1 c=2025 u=-1.0000000000 subseq=18
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=2 c=324 u=-1.0000000000 subseq=19 [Sample-CP] g=2 c=324 u=-1.0000000000 subseq=19
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=3 c=350 u=-1.0000000000 subseq=20 [Sample-CP] g=3 c=350 u=-1.0000000000 subseq=20
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=4 c=985 u=-1.0000000000 subseq=21 [Sample-CP] g=4 c=985 u=-1.0000000000 subseq=21
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=5 c=853 u=-1.0000000000 subseq=22 [Sample-CP] g=5 c=853 u=-1.0000000000 subseq=22
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=6 c=329 u=-1.0000000000 subseq=23 [Sample-CP] g=6 c=329 u=-1.0000000000 subseq=23
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=7 c=564 u=-1.0000000000 subseq=24 [Sample-CP] g=7 c=564 u=-1.0000000000 subseq=24
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=8 c=692 u=-1.0000000000 subseq=25 [Sample-CP] g=8 c=692 u=-1.0000000000 subseq=25
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=9 c=1702 u=-1.0000000000 subseq=26 [Sample-CP] g=9 c=1702 u=-1.0000000000 subseq=26
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=10 c=437 u=-1.0000000000 subseq=27 [Sample-CP] g=10 c=437 u=-1.0000000000 subseq=27
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=11 c=729 u=-1.0000000000 subseq=28 [Sample-CP] g=11 c=729 u=-1.0000000000 subseq=28
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=12 c=344 u=-1.0000000000 subseq=29 [Sample-CP] g=12 c=344 u=-1.0000000000 subseq=29
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=13 c=85 u=-1.0000000000 subseq=30 [Sample-CP] g=13 c=85 u=-1.0000000000 subseq=30
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=14 c=1668 u=-1.0000000000 subseq=31 [Sample-CP] g=14 c=1668 u=-1.0000000000 subseq=31
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Pipeline] Generated 8 frames [Pipeline] Generated 8 frames
[Pipeline] Generated 16 frames [Pipeline] Generated 16 frames
[Pipeline] Generated 24 frames [Pipeline] Generated 24 frames
[Pipeline] Generated 32 frames [Pipeline] Generated 32 frames
ggml_backend_cuda_graph_compute: CUDA graph warmup reset
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Pipeline] Generated 40 frames [Pipeline] Generated 40 frames
[Pipeline] Generated 48 frames [Pipeline] Generated 48 frames
[Pipeline] Generated 56 frames [Pipeline] Generated 56 frames
@@ -124,13 +141,13 @@ ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000
[Debug] output-audio: [122880] first4: 0.000465 0.000259 -0.001065 -0.000736 [Debug] output-audio: [122880] first4: 0.000465 0.000259 -0.001065 -0.000736
[Perf] PromptBuild 1.2 ms [Perf] PromptBuild 1.2 ms
[Perf] Prefill 12.8 ms (T_ctx prefill) [Perf] Prefill 13.3 ms (T_ctx prefill)
[Perf] TTFA 22.0 ms (first frame codes) [Perf] TTFA 23.1 ms (first frame codes)
[Perf] TalkerDecode 203.8 ms (64 frames, 3.18 ms/frame) [Perf] TalkerDecode 188.4 ms (64 frames, 2.94 ms/frame)
[Perf] CodePredictor 331.0 ms (5.17 ms/frame) [Perf] CodePredictor 303.3 ms (4.74 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 14.7 ms [Perf] CodecDecode 14.6 ms
[Perf] Total 564.5 ms (64 frames, 8.36 ms/frame AR, audio 5.12 s, RTF 0.110) [Perf] Total 521.9 ms (64 frames, 7.68 ms/frame AR, audio 5.12 s, RTF 0.102)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-CUDA0-F32.log
+25 -8
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -51,7 +51,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB [EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB
[WeightCtx] Loaded 20 tensors, 34.0 MB into backend [WeightCtx] Loaded 20 tensors, 34.0 MB into backend
[EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB [EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB
[Pipeline] Codec encoder lazy loaded in 49 ms [Pipeline] Codec encoder lazy loaded in 31 ms
[Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340 [Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340
[Debug] seanet-out: [430, 512] first4: -0.134336 13.731120 -0.351051 3.013485 [Debug] seanet-out: [430, 512] first4: -0.134336 13.731120 -0.351051 3.013485
[Debug] enc-transformer-out: [430, 512] first4: 0.525800 3.116711 -0.187038 0.631811 [Debug] enc-transformer-out: [430, 512] first4: 0.525800 3.116711 -0.187038 0.631811
@@ -98,24 +98,41 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Sample] step=1 c0=1902 u=-1.0000000000 subseq=16 [Sample] step=1 c0=1902 u=-1.0000000000 subseq=16
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=0 c=1924 u=-1.0000000000 subseq=17 [Sample-CP] g=0 c=1924 u=-1.0000000000 subseq=17
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=1 c=2025 u=-1.0000000000 subseq=18 [Sample-CP] g=1 c=2025 u=-1.0000000000 subseq=18
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=2 c=324 u=-1.0000000000 subseq=19 [Sample-CP] g=2 c=324 u=-1.0000000000 subseq=19
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=3 c=1501 u=-1.0000000000 subseq=20 [Sample-CP] g=3 c=1501 u=-1.0000000000 subseq=20
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=4 c=1252 u=-1.0000000000 subseq=21 [Sample-CP] g=4 c=1252 u=-1.0000000000 subseq=21
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=5 c=1831 u=-1.0000000000 subseq=22 [Sample-CP] g=5 c=1831 u=-1.0000000000 subseq=22
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=6 c=1544 u=-1.0000000000 subseq=23 [Sample-CP] g=6 c=1544 u=-1.0000000000 subseq=23
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=7 c=1058 u=-1.0000000000 subseq=24 [Sample-CP] g=7 c=1058 u=-1.0000000000 subseq=24
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=8 c=1673 u=-1.0000000000 subseq=25 [Sample-CP] g=8 c=1673 u=-1.0000000000 subseq=25
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=9 c=541 u=-1.0000000000 subseq=26 [Sample-CP] g=9 c=541 u=-1.0000000000 subseq=26
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=10 c=1162 u=-1.0000000000 subseq=27 [Sample-CP] g=10 c=1162 u=-1.0000000000 subseq=27
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=11 c=729 u=-1.0000000000 subseq=28 [Sample-CP] g=11 c=729 u=-1.0000000000 subseq=28
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=12 c=781 u=-1.0000000000 subseq=29 [Sample-CP] g=12 c=781 u=-1.0000000000 subseq=29
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=13 c=85 u=-1.0000000000 subseq=30 [Sample-CP] g=13 c=85 u=-1.0000000000 subseq=30
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=14 c=1435 u=-1.0000000000 subseq=31 [Sample-CP] g=14 c=1435 u=-1.0000000000 subseq=31
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Pipeline] Generated 8 frames [Pipeline] Generated 8 frames
[Pipeline] Generated 16 frames [Pipeline] Generated 16 frames
[Pipeline] Generated 24 frames [Pipeline] Generated 24 frames
[Pipeline] Generated 32 frames [Pipeline] Generated 32 frames
ggml_backend_cuda_graph_compute: CUDA graph warmup reset
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Pipeline] Generated 40 frames [Pipeline] Generated 40 frames
[Pipeline] Generated 48 frames [Pipeline] Generated 48 frames
[Pipeline] Generated 56 frames [Pipeline] Generated 56 frames
@@ -124,13 +141,13 @@ ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000
[Debug] output-audio: [122880] first4: 0.000739 0.000593 -0.000747 -0.000435 [Debug] output-audio: [122880] first4: 0.000739 0.000593 -0.000747 -0.000435
[Perf] PromptBuild 1.4 ms [Perf] PromptBuild 1.4 ms
[Perf] Prefill 27.2 ms (T_ctx prefill) [Perf] Prefill 27.4 ms (T_ctx prefill)
[Perf] TTFA 37.0 ms (first frame codes) [Perf] TTFA 37.5 ms (first frame codes)
[Perf] TalkerDecode 311.1 ms (64 frames, 4.86 ms/frame) [Perf] TalkerDecode 300.4 ms (64 frames, 4.69 ms/frame)
[Perf] CodePredictor 419.2 ms (6.55 ms/frame) [Perf] CodePredictor 388.9 ms (6.08 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 14.6 ms [Perf] CodecDecode 14.9 ms
[Perf] Total 774.6 ms (64 frames, 11.41 ms/frame AR, audio 5.12 s, RTF 0.151) [Perf] Total 734.2 ms (64 frames, 10.77 ms/frame AR, audio 5.12 s, RTF 0.143)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-CUDA0-Q4_K_M.log
+26 -9
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -33,7 +33,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Audio-Resample] Done: 380672 -> 414337 samples [Audio-Resample] Done: 380672 -> 414337 samples
[WeightCtx] Loaded 76 tensors, 34.9 MB into backend [WeightCtx] Loaded 76 tensors, 34.9 MB into backend
[SpeakerEncoder] Loaded: enc_dim=2048 sr=24000 mel_dim=128 hidden=512 mfa=1536 asp_attn=128 se=128 scale=8 [SpeakerEncoder] Loaded: enc_dim=2048 sr=24000 mel_dim=128 hidden=512 mfa=1536 asp_attn=128 se=128 scale=8
[Pipeline] Speaker encoder lazy loaded in 27 ms [Pipeline] Speaker encoder lazy loaded in 3 ms
[Debug] mel-spk: [1618, 128] first4: -6.330339 -6.170074 -6.011195 -6.243161 [Debug] mel-spk: [1618, 128] first4: -6.330339 -6.170074 -6.011195 -6.243161
[Debug] mel-hann: [1024] first4: 0.000000 0.000009 0.000038 0.000085 [Debug] mel-hann: [1024] first4: 0.000000 0.000009 0.000038 0.000085
[Debug] mel-basis: [128, 513] first4: 0.000000 0.033550 0.008569 0.000000 [Debug] mel-basis: [128, 513] first4: 0.000000 0.033550 0.008569 0.000000
@@ -51,7 +51,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB [EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB
[WeightCtx] Loaded 20 tensors, 34.0 MB into backend [WeightCtx] Loaded 20 tensors, 34.0 MB into backend
[EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB [EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB
[Pipeline] Codec encoder lazy loaded in 44 ms [Pipeline] Codec encoder lazy loaded in 7 ms
[Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340 [Debug] audio-input: [412800] first4: -0.000546 -0.001162 -0.000871 0.000340
[Debug] seanet-out: [430, 512] first4: -0.134336 13.731120 -0.351051 3.013485 [Debug] seanet-out: [430, 512] first4: -0.134336 13.731120 -0.351051 3.013485
[Debug] enc-transformer-out: [430, 512] first4: 1.140990 3.713432 0.131578 0.616251 [Debug] enc-transformer-out: [430, 512] first4: 1.140990 3.713432 0.131578 0.616251
@@ -98,19 +98,33 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Sample] step=1 c0=99 u=-1.0000000000 subseq=16 [Sample] step=1 c0=99 u=-1.0000000000 subseq=16
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=0 c=43 u=-1.0000000000 subseq=17 [Sample-CP] g=0 c=43 u=-1.0000000000 subseq=17
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=1 c=1859 u=-1.0000000000 subseq=18 [Sample-CP] g=1 c=1859 u=-1.0000000000 subseq=18
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=2 c=22 u=-1.0000000000 subseq=19 [Sample-CP] g=2 c=22 u=-1.0000000000 subseq=19
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=3 c=239 u=-1.0000000000 subseq=20 [Sample-CP] g=3 c=239 u=-1.0000000000 subseq=20
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=4 c=915 u=-1.0000000000 subseq=21 [Sample-CP] g=4 c=915 u=-1.0000000000 subseq=21
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=5 c=2019 u=-1.0000000000 subseq=22 [Sample-CP] g=5 c=2019 u=-1.0000000000 subseq=22
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=6 c=329 u=-1.0000000000 subseq=23 [Sample-CP] g=6 c=329 u=-1.0000000000 subseq=23
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=7 c=241 u=-1.0000000000 subseq=24 [Sample-CP] g=7 c=241 u=-1.0000000000 subseq=24
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=8 c=1004 u=-1.0000000000 subseq=25 [Sample-CP] g=8 c=1004 u=-1.0000000000 subseq=25
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=9 c=826 u=-1.0000000000 subseq=26 [Sample-CP] g=9 c=826 u=-1.0000000000 subseq=26
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=10 c=1603 u=-1.0000000000 subseq=27 [Sample-CP] g=10 c=1603 u=-1.0000000000 subseq=27
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=11 c=1160 u=-1.0000000000 subseq=28 [Sample-CP] g=11 c=1160 u=-1.0000000000 subseq=28
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=12 c=1759 u=-1.0000000000 subseq=29 [Sample-CP] g=12 c=1759 u=-1.0000000000 subseq=29
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=13 c=591 u=-1.0000000000 subseq=30 [Sample-CP] g=13 c=591 u=-1.0000000000 subseq=30
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=14 c=901 u=-1.0000000000 subseq=31 [Sample-CP] g=14 c=901 u=-1.0000000000 subseq=31
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
@@ -126,6 +140,7 @@ ggml_backend_cuda_graph_compute: CUDA graph warmup complete
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Pipeline] Generated 8 frames [Pipeline] Generated 8 frames
[Pipeline] Generated 16 frames [Pipeline] Generated 16 frames
[Pipeline] Generated 24 frames [Pipeline] Generated 24 frames
@@ -144,6 +159,8 @@ ggml_backend_cuda_graph_compute: CUDA graph warmup reset
ggml_backend_cuda_graph_compute: CUDA graph warmup reset ggml_backend_cuda_graph_compute: CUDA graph warmup reset
ggml_backend_cuda_graph_compute: CUDA graph warmup reset ggml_backend_cuda_graph_compute: CUDA graph warmup reset
ggml_backend_cuda_graph_compute: CUDA graph warmup reset ggml_backend_cuda_graph_compute: CUDA graph warmup reset
ggml_backend_cuda_graph_compute: CUDA graph warmup reset
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
@@ -166,13 +183,13 @@ ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Debug] codes-full: [64, 16] first4: 27.000000 1042.000000 390.000000 881.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1042.000000 390.000000 881.000000
[Debug] output-audio: [122880] first4: 0.000087 0.000212 -0.000383 -0.000346 [Debug] output-audio: [122880] first4: 0.000087 0.000212 -0.000383 -0.000346
[Perf] PromptBuild 55.2 ms [Perf] PromptBuild 55.2 ms
[Perf] Prefill 14.2 ms (T_ctx prefill) [Perf] Prefill 14.4 ms (T_ctx prefill)
[Perf] TTFA 77.1 ms (first frame codes) [Perf] TTFA 78.1 ms (first frame codes)
[Perf] TalkerDecode 231.8 ms (64 frames, 3.62 ms/frame) [Perf] TalkerDecode 220.3 ms (64 frames, 3.44 ms/frame)
[Perf] CodePredictor 358.2 ms (5.60 ms/frame) [Perf] CodePredictor 327.3 ms (5.11 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 15.8 ms [Perf] CodecDecode 15.7 ms
[Perf] Total 676.2 ms (64 frames, 9.22 ms/frame AR, audio 5.12 s, RTF 0.132) [Perf] Total 634.2 ms (64 frames, 8.56 ms/frame AR, audio 5.12 s, RTF 0.124)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-CUDA0-Q8_0.log
+24 -7
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -98,24 +98,41 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Sample] step=1 c0=1902 u=-1.0000000000 subseq=16 [Sample] step=1 c0=1902 u=-1.0000000000 subseq=16
ggml_backend_cuda_graph_compute: CUDA graph warmup complete ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=0 c=1924 u=-1.0000000000 subseq=17 [Sample-CP] g=0 c=1924 u=-1.0000000000 subseq=17
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=1 c=2025 u=-1.0000000000 subseq=18 [Sample-CP] g=1 c=2025 u=-1.0000000000 subseq=18
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=2 c=324 u=-1.0000000000 subseq=19 [Sample-CP] g=2 c=324 u=-1.0000000000 subseq=19
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=3 c=1501 u=-1.0000000000 subseq=20 [Sample-CP] g=3 c=1501 u=-1.0000000000 subseq=20
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=4 c=407 u=-1.0000000000 subseq=21 [Sample-CP] g=4 c=407 u=-1.0000000000 subseq=21
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=5 c=1452 u=-1.0000000000 subseq=22 [Sample-CP] g=5 c=1452 u=-1.0000000000 subseq=22
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=6 c=1544 u=-1.0000000000 subseq=23 [Sample-CP] g=6 c=1544 u=-1.0000000000 subseq=23
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=7 c=1058 u=-1.0000000000 subseq=24 [Sample-CP] g=7 c=1058 u=-1.0000000000 subseq=24
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=8 c=692 u=-1.0000000000 subseq=25 [Sample-CP] g=8 c=692 u=-1.0000000000 subseq=25
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=9 c=1702 u=-1.0000000000 subseq=26 [Sample-CP] g=9 c=1702 u=-1.0000000000 subseq=26
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=10 c=362 u=-1.0000000000 subseq=27 [Sample-CP] g=10 c=362 u=-1.0000000000 subseq=27
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=11 c=729 u=-1.0000000000 subseq=28 [Sample-CP] g=11 c=729 u=-1.0000000000 subseq=28
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=12 c=781 u=-1.0000000000 subseq=29 [Sample-CP] g=12 c=781 u=-1.0000000000 subseq=29
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=13 c=82 u=-1.0000000000 subseq=30 [Sample-CP] g=13 c=82 u=-1.0000000000 subseq=30
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Sample-CP] g=14 c=1435 u=-1.0000000000 subseq=31 [Sample-CP] g=14 c=1435 u=-1.0000000000 subseq=31
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Pipeline] Generated 8 frames [Pipeline] Generated 8 frames
[Pipeline] Generated 16 frames [Pipeline] Generated 16 frames
[Pipeline] Generated 24 frames [Pipeline] Generated 24 frames
[Pipeline] Generated 32 frames [Pipeline] Generated 32 frames
ggml_backend_cuda_graph_compute: CUDA graph warmup reset
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Pipeline] Generated 40 frames [Pipeline] Generated 40 frames
[Pipeline] Generated 48 frames [Pipeline] Generated 48 frames
[Pipeline] Generated 56 frames [Pipeline] Generated 56 frames
@@ -123,14 +140,14 @@ ggml_backend_cuda_graph_compute: CUDA graph warmup complete
[Pipeline] Generation done : 64 frames [Pipeline] Generation done : 64 frames
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000
[Debug] output-audio: [122880] first4: 0.000596 0.000259 -0.001224 -0.000817 [Debug] output-audio: [122880] first4: 0.000596 0.000259 -0.001224 -0.000817
[Perf] PromptBuild 1.4 ms [Perf] PromptBuild 1.5 ms
[Perf] Prefill 14.6 ms (T_ctx prefill) [Perf] Prefill 15.2 ms (T_ctx prefill)
[Perf] TTFA 22.3 ms (first frame codes) [Perf] TTFA 24.0 ms (first frame codes)
[Perf] TalkerDecode 166.6 ms (64 frames, 2.60 ms/frame) [Perf] TalkerDecode 153.4 ms (64 frames, 2.40 ms/frame)
[Perf] CodePredictor 277.8 ms (4.34 ms/frame) [Perf] CodePredictor 245.1 ms (3.83 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 15.0 ms [Perf] CodecDecode 15.0 ms
[Perf] Total 476.5 ms (64 frames, 6.95 ms/frame AR, audio 5.12 s, RTF 0.093) [Perf] Total 431.5 ms (64 frames, 6.23 ms/frame AR, audio 5.12 s, RTF 0.084)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-Vulkan0-BF16.log
+8 -8
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -122,14 +122,14 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Pipeline] Generation done : 64 frames [Pipeline] Generation done : 64 frames
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000
[Debug] output-audio: [122880] first4: 0.000515 0.000357 -0.000915 -0.000575 [Debug] output-audio: [122880] first4: 0.000515 0.000357 -0.000915 -0.000575
[Perf] PromptBuild 1.7 ms [Perf] PromptBuild 1.9 ms
[Perf] Prefill 31.0 ms (T_ctx prefill) [Perf] Prefill 31.2 ms (T_ctx prefill)
[Perf] TTFA 623.5 ms (first frame codes) [Perf] TTFA 41.1 ms (first frame codes)
[Perf] TalkerDecode 247.6 ms (64 frames, 3.87 ms/frame) [Perf] TalkerDecode 247.4 ms (64 frames, 3.87 ms/frame)
[Perf] CodePredictor 986.5 ms (15.41 ms/frame) [Perf] CodePredictor 418.8 ms (6.54 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 30.9 ms [Perf] CodecDecode 35.3 ms
[Perf] Total 1299.0 ms (64 frames, 19.29 ms/frame AR, audio 5.12 s, RTF 0.254) [Perf] Total 735.7 ms (64 frames, 10.41 ms/frame AR, audio 5.12 s, RTF 0.144)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-Vulkan0-F32.log
+8 -8
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -122,14 +122,14 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Pipeline] Generation done : 64 frames [Pipeline] Generation done : 64 frames
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000
[Debug] output-audio: [122880] first4: 0.000673 0.000478 -0.000828 -0.000482 [Debug] output-audio: [122880] first4: 0.000673 0.000478 -0.000828 -0.000482
[Perf] PromptBuild 21.5 ms [Perf] PromptBuild 2.3 ms
[Perf] Prefill 1361.8 ms (T_ctx prefill) [Perf] Prefill 19.7 ms (T_ctx prefill)
[Perf] TTFA 1740.1 ms (first frame codes) [Perf] TTFA 31.0 ms (first frame codes)
[Perf] TalkerDecode 518.2 ms (64 frames, 8.10 ms/frame) [Perf] TalkerDecode 367.9 ms (64 frames, 5.75 ms/frame)
[Perf] CodePredictor 842.7 ms (13.17 ms/frame) [Perf] CodePredictor 504.1 ms (7.88 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 1373.9 ms [Perf] CodecDecode 28.8 ms
[Perf] Total 4119.4 ms (64 frames, 21.27 ms/frame AR, audio 5.12 s, RTF 0.805) [Perf] Total 924.0 ms (64 frames, 13.63 ms/frame AR, audio 5.12 s, RTF 0.180)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-Vulkan0-Q4_K_M.log
+8 -8
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -122,14 +122,14 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Pipeline] Generation done : 64 frames [Pipeline] Generation done : 64 frames
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 417.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 417.000000
[Debug] output-audio: [122880] first4: -0.000101 0.000003 -0.000779 -0.000457 [Debug] output-audio: [122880] first4: -0.000101 0.000003 -0.000779 -0.000457
[Perf] PromptBuild 1050.5 ms [Perf] PromptBuild 2.6 ms
[Perf] Prefill 1572.6 ms (T_ctx prefill) [Perf] Prefill 16.6 ms (T_ctx prefill)
[Perf] TTFA 2788.5 ms (first frame codes) [Perf] TTFA 25.6 ms (first frame codes)
[Perf] TalkerDecode 269.8 ms (64 frames, 4.22 ms/frame) [Perf] TalkerDecode 175.7 ms (64 frames, 2.75 ms/frame)
[Perf] CodePredictor 478.1 ms (7.47 ms/frame) [Perf] CodePredictor 328.4 ms (5.13 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 29.4 ms [Perf] CodecDecode 31.6 ms
[Perf] Total 3410.1 ms (64 frames, 11.69 ms/frame AR, audio 5.12 s, RTF 0.666) [Perf] Total 556.1 ms (64 frames, 7.88 ms/frame AR, audio 5.12 s, RTF 0.109)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
tests/clone-Vulkan0-Q8_0.log
+8 -8
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 3e3b6c1 (2026-07-04) [Qwen] qwentts.cpp f84fc05 (2026-07-04)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB): 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 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/qwentts.cpp/build/libggml-cuda.so load_backend: loaded CUDA backend from /mnt/workspace/git/qwentts.cpp/build/libggml-cuda.so
@@ -122,14 +122,14 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Pipeline] Generation done : 64 frames [Pipeline] Generation done : 64 frames
[Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000 [Debug] codes-full: [64, 16] first4: 27.000000 1408.000000 1824.000000 400.000000
[Debug] output-audio: [122880] first4: 0.000658 0.000394 -0.000943 -0.000566 [Debug] output-audio: [122880] first4: 0.000658 0.000394 -0.000943 -0.000566
[Perf] PromptBuild 1303.3 ms [Perf] PromptBuild 2.6 ms
[Perf] Prefill 1974.9 ms (T_ctx prefill) [Perf] Prefill 16.7 ms (T_ctx prefill)
[Perf] TTFA 3439.7 ms (first frame codes) [Perf] TTFA 25.8 ms (first frame codes)
[Perf] TalkerDecode 196.2 ms (64 frames, 3.07 ms/frame) [Perf] TalkerDecode 199.6 ms (64 frames, 3.12 ms/frame)
[Perf] CodePredictor 488.2 ms (7.63 ms/frame) [Perf] CodePredictor 331.5 ms (5.18 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb) [Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 30.3 ms [Perf] CodecDecode 30.1 ms
[Perf] Total 3994.3 ms (64 frames, 10.70 ms/frame AR, audio 5.12 s, RTF 0.780) [Perf] Total 581.8 ms (64 frames, 8.30 ms/frame AR, audio 5.12 s, RTF 0.114)
[WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16 [WAV] Wrote cpp/clone/clone-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav [Pipeline] Wrote 122880 samples (5.12 s) -> cpp/clone/clone-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo... [Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...