SeedVR2 Installation Guide (Version 2.5.0 πŸŽ‰)

AI ζŠ€θ‘“γ€η”»εƒγƒ»ε‹•η”»γƒ„γƒΌγƒ«
4

Step 6: Enable torch.compile (Optional)

The new Version 2.5 support torch.compile:
According to official claim, 20-40% DiT speedup and 15-25% VAE speedup with full graph compilation

But Triton is required for torch.compile with inductor backend

If you do not have Trition installed, you will get warning.

━━━━━━━━ Phase 1: VAE encoding ━━━━━━━━

[15:13:47.522] ❌ [ERROR] Cannot use torch.compile with 'inductor' backend: Triton is not installed.

Triton is required for the inductor backend which performs kernel fusion and optimization.

To fix this issue:
  1. Install Triton: pip install triton
  2. OR change backend to 'cudagraphs' (lightweight, no Triton needed)
  3. OR disable torch.compile

For more info: https://github.com/triton-lang/triton
[15:13:47.523] ⚠️ [WARNING] torch.compile failed for VAE submodules: torch.compile with inductor backend requires Triton. Install with: pip install triton
[15:13:47.523] ⚠️ [WARNING]   Falling back to uncompiled VAE

If you do not have Trition installed, you will get warning.

━━━━━━━━ Phase 2: DiT upscaling ━━━━━━━━

[15:13:49.856] ❌ [ERROR] Cannot use torch.compile with 'inductor' backend: Triton is not installed.

Triton is required for the inductor backend which performs kernel fusion and optimization.

To fix this issue:
  1. Install Triton: pip install triton
  2. OR change backend to 'cudagraphs' (lightweight, no Triton needed)
  3. OR disable torch.compile

For more info: https://github.com/triton-lang/triton
[15:13:49.857] ⚠️ [WARNING] torch.compile failed for DiT: torch.compile with inductor backend requires Triton. Install with: pip install triton
[15:13:49.857] ⚠️ [WARNING]   Falling back to uncompiled model