Downloads · 30 days
0
ltx23-shares
yitongl/ltx23-shares
ltx23-shares is a machine learning model from yitongl. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Generated on a single NVIDIA B300 with the SGLang multimodalgen stack. Steady-state (warmup-excluded) speedups:
Access
Public
Updated Jun 19, 2026
Repo size
41.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.zip20.8 MB · 50%
At a glance
- License
- other
- Access
- Public
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026
- SHA
- c4be812c
Model card
From the Hugging Face model README
Sol-LTX-Infer demo videos (B300 / sm_103, CUDA 13)
Generated on a single NVIDIA B300 with the SGLang multimodal_gen stack. Steady-state (warmup-excluded) speedups:
| model | baseline | fullopt | fullopt + real NVFP4 |
|---|---|---|---|
| LTX-2.3 (1080p/10s, 2-stage HQ) | 99.3s | 44.3s (2.24x) | 41.4s (2.40x) |
| Cosmos3-Super 64B (720p/189f, 1 GPU) | 345.0s | 170.1s (2.03x) | 130.3s (2.65x) |
| SANA-Video 2B (480p) | 41.1s | (EasyCache+fusion+compile) | — |
fullopt = cache/sparse/fusion stack; +NVFP4 = non-TE shape-aware NVFP4 GEMM
(jit CUTLASS / autotuned flashinfer per shape). See repo EXECUTION_LOG.md.
- License
- other
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026