FP8 GEMM-trunk quantization of the Stable Audio 3 medium DiT, built from
stabilityai/stable-audio-3-optimized
onnx/sa3-m/dit_fp16mixed.onnx
with the
producer recipe in
Stability-AI/stable-audio-3 PR #47
(
build/make_calib.py
+
build/build_dit_fp8.py
). This is a derivative of
Stability AI's model weights and is distributed under the Stability AI
Community License; see the base model for terms.
Contents
onnx/sa3-m/dit_fp8.onnx
+
dit_fp8.onnx.data
— the quantized ONNX
(arch-independent; compile with
build_from_onnx.py sa3-m-fp8
, plain
STRONGLY_TYPED, no ModelOpt needed)
tensorRT/sm_120/sa3-m/dit_fp8.trt
— prebuilt engine for RTX 50xx
(sm_120), TensorRT 10.16.1.11. TRT engines are not portable across GPU
architectures or TRT minor versions; rebuild from the ONNX for anything else.
Validation (vs the FP16-mixed engine, 47 prompts x 8 sigmas, L=646, RTX 5090)
8-step compounded euler final-latent cosine over 47 prompts: mean 0.953,
median 0.957, worst 0.873 (the rollout is chaotic; a 1e-3 input
perturbation alone compounds to ~0.967, so this is a guide, not a gate)
decoded audio under the production pingpong sampler tracks the FP16-mixed
generation at ~0.90 RMS-curve correlation (same conditioning and seeds) and
was validated by listening: the published sm_120 engine here is the exact
engine that passed that test
step latency B=1 L=646:
10.6-11.0 ms vs ~18.7-19.4 ms FP16-mixed (
1.8x)
under the stochastic pingpong sampler the engine produces a different but
comparable sample
Inputs/outputs are FP32, drop-in for the FP16-mixed DiT engine
(
sa3_trt --precision fp8
, paired with the FP16-mixed decoder).
Runs of ryanontheinside stable-audio-3-optimized-fp8 on huggingface.co
5
Total runs
0
24-hour runs
0
3-day runs
1
7-day runs
1
30-day runs
More Information About stable-audio-3-optimized-fp8 huggingface.co Model
More stable-audio-3-optimized-fp8 license Visit here:
stable-audio-3-optimized-fp8 huggingface.co is an AI model on huggingface.co that provides stable-audio-3-optimized-fp8's model effect (), which can be used instantly with this ryanontheinside stable-audio-3-optimized-fp8 model. huggingface.co supports a free trial of the stable-audio-3-optimized-fp8 model, and also provides paid use of the stable-audio-3-optimized-fp8. Support call stable-audio-3-optimized-fp8 model through api, including Node.js, Python, http.
stable-audio-3-optimized-fp8 huggingface.co is an online trial and call api platform, which integrates stable-audio-3-optimized-fp8's modeling effects, including api services, and provides a free online trial of stable-audio-3-optimized-fp8, you can try stable-audio-3-optimized-fp8 online for free by clicking the link below.
ryanontheinside stable-audio-3-optimized-fp8 online free url in huggingface.co:
stable-audio-3-optimized-fp8 is an open source model from GitHub that offers a free installation service, and any user can find stable-audio-3-optimized-fp8 on GitHub to install. At the same time, huggingface.co provides the effect of stable-audio-3-optimized-fp8 install, users can directly use stable-audio-3-optimized-fp8 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
stable-audio-3-optimized-fp8 install url in huggingface.co: