v0.5 CRITICAL: Fix patch_size to scale with image size (L≤256 always), reduce d_state for speed, add config table

v0.4: Use mambapy.pscan (proven, grad-safe parallel scan) — no more torch.associative_scan

v0.3: PARALLEL SSM scan (torch.associative_scan), patch_size 4→8, no more Python for-loop

Fix: remove duplicate forward method in LiquidSSMBlock, clean up dead code"

CRITICAL FIX: OOM on T4 — rewrite SSM scan to not materialize 4D tensors, add gradient checkpointing, optimize Liquid CfC memory

Add model.py — core LiquidFlow architecture