Use precompiled AOTI transformer blocks (ZeroGPU speedup)

#1
by linoyts HF Staff - opened
LTX Community org
edited Jun 17

Swaps the live LoRA adapter for a fused LoRA + loads the precompiled ahead-of-time transformer blocks from a public graph-only repo on the first GPU call.

linoyts changed pull request status to merged

Sign up or log in to comment