Patch embed to joint attention input
Complete input processing pipeline for SD3.5 that converts spatial image latents through patch embedding with positional encoding, processes timestep and pooled projections into temporal conditioning, and projects context embeddings. Combines three embedding pathways: image patches, temporal conditioning, and text context.
Reported evidence · last observed 2026-08-21. Reported by source; not independently reproduced. No public source. License unknown.
Current records
Workloadsuite of 16 cases · mean latencyinner_dim = 2432 · patch_size = 2 · in_channels = 16 · num_patches = 4096 · sample_size = 128 · sinusoidal_dim = 256 · attention_head_dim = 64 · pos_embed_max_size = 192 · joint_attention_dim = 4096 · num_attention_heads = 38 · sinusoidal_half_dim = 128 · pooled_projection_dim = 2048 · caption_projection_dim = 243216 cases
Not measured on H100 for this workload. Challenges →
1254.6µs67% SOL1.00×Reported · license unknown · no source2026-08-21
Measured exactly what you asked. Reported by source; not independently reproduced.
2254.8µs67% SOL1.00×Reported · license unknown · no source2026-08-23
Measured exactly what you asked. Reported by source; not independently reproduced.
3259.3µs67% SOL1.02×Reported · license unknown · no source2026-08-15
Measured exactly what you asked. Reported by source; not independently reproduced.
4307.3µs62% SOL1.21×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
5313.1µs61% SOL1.23×Reported · license unknown · no source2026-07-11
Measured exactly what you asked. Reported by source; not independently reproduced.
6318.0µs61% SOL1.25×Reported · license unknown · no source2026-07-17
Measured exactly what you asked. Reported by source; not independently reproduced.
7321.1µs61% SOL1.26×Reported · license unknown · no source2026-08-04
Measured exactly what you asked. Reported by source; not independently reproduced.
8328.6µs60% SOL1.29×Reported · license unknown · no source2026-07-14
Measured exactly what you asked. Reported by source; not independently reproduced.
9331.8µs60% SOL1.30×Reported · license unknown · no source2026-08-24
Measured exactly what you asked. Reported by source; not independently reproduced.
10352.1µs58% SOL1.38×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
11352.3µs58% SOL1.38×Reported · license unknown · no source2026-08-19
Measured exactly what you asked. Reported by source; not independently reproduced.
12373.0µs56% SOL1.47×Reported · license unknown · no source2026-08-18
Measured exactly what you asked. Reported by source; not independently reproduced.
13376.6µs56% SOL1.48×Reported · license unknown · no source2026-08-17
Measured exactly what you asked. Reported by source; not independently reproduced.
14376.8µs56% SOL1.48×Reported · license unknown · no source2026-08-17
Measured exactly what you asked. Reported by source; not independently reproduced.
15406.1µs54% SOL1.60×Reported · license unknown · no source2026-08-17
Measured exactly what you asked. Reported by source; not independently reproduced.
16424.3µs53% SOL1.67×Reported · license unknown · no source2026-08-13
Measured exactly what you asked. Reported by source; not independently reproduced.
17444.0µs51% SOL1.74×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
18453.9µs51% SOL1.78×Reported · license unknown · no source2026-08-17
Measured exactly what you asked. Reported by source; not independently reproduced.
19474.9µs50% SOL1.87×Reported · license unknown · no source2026-08-13
Measured exactly what you asked. Reported by source; not independently reproduced.
20530.2µs46% SOL2.08×Reported · license unknown · no source2026-07-25
Measured exactly what you asked. Reported by source; not independently reproduced.
21540.5µs46% SOL2.12×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
22867.5µs34% SOL3.41×Reported · license unknown · no source2026-08-12
Measured exactly what you asked. Reported by source; not independently reproduced.