Downloads · 30 days
0
LTX-2.3-Native-Transformer-GroupA-sm120-cu130-r20
linoyts/LTX-2.3-Native-Transformer-GroupA-sm120-cu130-r20
LTX-2.3-Native-Transformer-GroupA-sm120-cu130-r20 is a machine learning model from linoyts. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch.
AOTI precompiled graph of BasicAVTransformerBlock (submodule transformerblocks) for the native ltxcore LTXModel (AudioVideo, distilled IC-LoRA path).
Access
Public
Updated Jun 19, 2026
Repo size
2 MB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.pt22 MB · 99%
At a glance
- Library
- pytorch
- Access
- Public
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026
- SHA
- 24ec6889
Model card
From the Hugging Face model README
LTX-2.3-Native-Transformer-GroupA (native LTX-2 backend)
AOTI precompiled graph of BasicAVTransformerBlock (submodule transformer_blocks) for the native ltx_core LTXModel (AudioVideo, distilled IC-LoRA path).
- Backend: github.com/Lightricks/LTX-2 @
ae855f8538843825f9015a419cf4ba5edaf5eec2 - Compiled on: NVIDIA RTX PRO 6000 Blackwell Server Edition sm120 / cu130, torch 2.12.0+cu130
- Capture res 1024x1024, 33f. Correctness vs eager: rel max|Δ| video=1.48e-02
Consumption: aoti_load onto transformer.velocity_model, then patch _process_transformer_blocks to flatten TransformerArgs -> compiled flat block -> replace(x=...). See job.py / LTX2_NATIVE_AOTI_PROGRESS.md.
- Library
- pytorch
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026