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
2026-07-25 18:56:39 +02:00
parent d03ffb97f9
commit 13686e8d34
12 changed files with 163 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/clone-CPU-BF16.log
+13 -13
View File
@@ -1,4 +1,4 @@
[Qwen] qwentts.cpp 521503f (2026-07-20)
[Qwen] qwentts.cpp 710a52a (2026-07-25)
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/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
[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
[Pipeline] Codec encoder lazy loaded in 43 ms
[Pipeline] Codec encoder lazy loaded in 41 ms
[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] enc-transformer-out: [430, 512] first4: 0.526661 3.208130 -0.164395 0.605249
@@ -76,7 +76,7 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Debug] talker-hidden-prefill-l27: [225, 2048] first4: 7.054070 -34.409252 -7.069129 28.624571
[Debug] talker-hidden-prefill-final: [225, 2048] first4: 0.240086 -1.222942 -0.223565 0.888025
[Debug] talker-logits-prefill: [3072] first4: 1.339535 -7.642556 -6.988994 -10.529062
[Batch] Admit slot=0 T_ctx=225 prefill=384.7 ms build=2.5 ms (stall for 0 active slots)
[Batch] Admit slot=0 T_ctx=225 prefill=382.1 ms build=2.1 ms (stall for 0 active slots)
[Sample] step=0 c0=27 u=-1.0000000000 subseq=0
[Debug] codes-step0: [16] first4: 27.000000 1408.000000 1824.000000 400.000000
[Debug] next-emb-step0: [2048] first4: 0.073552 -0.034240 -0.008814 0.042007
@@ -92,15 +92,15 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Pipeline] Generated 64 frames (slot 0)
[Pipeline] Generation done : 64 frames
[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
[Perf] PromptBuild 2.5 ms
[Perf] Prefill 384.7 ms (T_ctx prefill)
[Perf] TTFA 1506.9 ms (first frame codes)
[Perf] TalkerDecode 2886.2 ms (64 frames, 45.10 ms/frame)
[Perf] CodePredictor 1518.3 ms (23.72 ms/frame)
[Debug] output-audio: [122880] first4: 0.000365 0.000165 -0.001043 -0.000566
[Perf] PromptBuild 2.1 ms
[Perf] Prefill 382.1 ms (T_ctx prefill)
[Perf] TTFA 1482.8 ms (first frame codes)
[Perf] TalkerDecode 2862.8 ms (64 frames, 44.73 ms/frame)
[Perf] CodePredictor 1428.0 ms (22.31 ms/frame)
[Perf] HostCompose 0.1 ms (c0 sample + next emb)
[Perf] CodecDecode 968.0 ms
[Perf] Total 6854.8 ms (64 frames, 68.82 ms/frame AR, audio 5.12 s, RTF 1.339)
[Perf] CodecDecode 2259.3 ms
[Perf] Total 8010.2 ms (64 frames, 67.05 ms/frame AR, audio 5.12 s, RTF 1.564)
[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
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
@@ -151,5 +151,5 @@ load_backend: loaded CPU backend from /mnt/workspace/git/qwentts.cpp/build/libgg
[Cossim] SpkASP cos: 0.999999 max: 2.2756e-03 mean: 1.8859e-04
[Cossim] SpeakerEmb cos: 1.000000 max: 6.4747e-04 mean: 1.3471e-04
[Cossim] CodesFull exact: 3.47% (1008 values)
[Cossim] Audio cos: -0.007662
[Cossim] WAV stft_cos: 0.207437 samples: 120960
[Cossim] Audio cos: -0.006883
[Cossim] WAV stft_cos: 0.209811 samples: 120960