Hugging Face's logo

stabilityai
/
stable-audio-3-optimized

Text-to-Audio
Stable Audio 3
LiteRT
ONNX
English
audio-generation
music
sound-effects
diffusion
Model card Files
xet
 Community
8
stable-audio-3-optimized / tensorRT /sm_90

Commit History

Upload tensorRT/sm_90/sa3-m/dit_fp8.trt with huggingface_hub
feddb8b
verified

cortexelus commited on

Fix the bf16 medium DiT: bake RoPE's tables into the graph (clipping 3.112% -> 0.014%) (#5)
6152b1d

cortexelus commited on

Rebuild medium DiT fp16-mixed engines (sm_90 + new sm_120): attention now fuses, 4.3x faster (#4)
06debc3

cortexelus commited on

Add bf16 medium DiT TRT engine (sm_90) — FMHA-fused, medium default (#1)
9a38efb

mattricesound cortexelus commited on

Add FP32 SAME-L + SAME-S TRT decoders
773ac48

Cortexelus Claude Opus 4.7 (1M context) commited on

Decoder ONNX: clip+scale in FP32 before int32 cast
a429ffa

Cortexelus Claude Opus 4.7 (1M context) commited on

DiT engines: replace BF16 with FP16-mixed (FP32 islands) + add FP32 variants
97651ef

Cortexelus Claude Opus 4.7 (1M context) commited on

DiT TRT engines: rebuild with profile min=1 (sm_90)
5f27021

Cortexelus Claude Opus 4.7 (1M context) commited on

T5Gemma: FP16-mixed (FP32 attention island) — fixes BF16 numerical bug
23f5c64

Cortexelus commited on

Decoder TRT engines: PCM-baked-in (sm_90)
106e6fd

Cortexelus commited on

Drop L-range suffix from SAME-L decoder filename
633bd26

Cortexelus commited on

Reorganize tensorRT/ into per-arch subdirs; rebuild DiT engines with conditioner baked in
08c1abe

Cortexelus commited on