CJ Carr

cortexelus's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 1 day ago

stabilityai/stable-audio-3-optimized

Text-to-Audio • Updated 1 day ago • 3.47k • 27

New activity in stabilityai/stable-audio-3-optimized 3 days ago

sm_120 sa3-m: add the fp8 medium-DiT tier (176 fp8 GEMM + 96 bf16 fused MHA, 1.43-1.95x vs fp16mixed)

#7 opened 3 days ago by

cortexelus

New activity in stabilityai/stable-audio-3-optimized 4 days ago

sm_120 SAME-L: AOT (graph-capturable) engines + tensorRT/README.md

#6 opened 4 days ago by

cortexelus

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

1

#5 opened 4 days ago by

cortexelus

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

2

#4 opened 4 days ago by

cortexelus

Fix medium DiT FP16-mixed ONNX: bound the RoPE island so attention fuses (4.3x faster, cos 1.0000)

#3 opened 4 days ago by

cortexelus

New activity in stabilityai/stable-audio-3-optimized 19 days ago

Add MLX base-model DiT weights for LoRA training

#2 opened 19 days ago by

cortexelus

Add bf16 medium DiT TRT engine (sm_90) — FMHA-fused, medium default

#1 opened 19 days ago by

cortexelus

updated 3 models 21 days ago

stabilityai/stable-audio-3-small-music-base

Text-to-Audio • 0.6B • Updated 21 days ago • 2.09k • 18

stabilityai/stable-audio-3-small-sfx-base

Text-to-Audio • 0.6B • Updated 21 days ago • 2.6k • 10

stabilityai/stable-audio-3-medium-base

Text-to-Audio • 2B • Updated 21 days ago • 11.9k • 24

updated 2 models 27 days ago

stabilityai/stable-audio-3-optimized

Text-to-Audio • Updated 1 day ago • 3.47k • 27

stabilityai/stable-audio-3-optimized

Text-to-Audio • Updated 1 day ago • 3.47k • 27