"""Gate for --fastfp (Anderson z*) and --bf16polish: endpoint parity + residual + eval-count/time vs the 150-step Euler reference, on two operators (deeply-trained fast-adaptive + near-edge s2000 — the hard case: Anderson historically fails on cycling ops, s2000's marginal band is the stress test). GPU shared with abl_pair — timings are relative, parity/evals exact.""" import time, torch import lt_ep_train as L for name, path in (('s2000', 'runs/redx_traj/s2000.pt'), ('fast-adaptive', 'runs/ep_fast_adaptive.pt')): torch.manual_seed(0) blk = L.EQBlock(512, 16, 256, 256, c=1.0, attn_mode='thick'); blk.qknorm = True ck = torch.load(path, map_location=L.dev) with torch.no_grad(): for p, w in zip(blk.allp, ck['allp']): p.copy_(w.to(L.dev)) torch.manual_seed(42) idx, _ = L.get_batch('train', 24, 256) xin = blk.embed(idx).detach() torch.cuda.synchronize(); t = time.time() z_ref = L.relax(blk, xin.clone(), xin, 150, 0.1) torch.cuda.synchronize(); t_ref = time.time() - t r_ref = (L.relax(blk, z_ref, xin, 1, 0.1) - z_ref).norm().item() print(f"[{name}] euler150 : {t_ref:5.2f}s res={r_ref:.2e}", flush=True) torch.cuda.synchronize(); t = time.time() z_aa, evals = L.anderson_relax(blk, xin.clone(), xin, 150, 0.1) torch.cuda.synchronize(); t_aa = time.time() - t r_aa = (L.relax(blk, z_aa, xin, 1, 0.1) - z_aa).norm().item() zd = ((z_aa - z_ref).norm() / (z_ref.norm() + 1e-12)).item() print(f"[{name}] anderson : {t_aa:5.2f}s res={r_aa:.2e} evals={evals} z-diff={zd:.2e}", flush=True) blk.bf16polish = 20 torch.cuda.synchronize(); t = time.time() z_bf = L.relax(blk, xin.clone(), xin, 150, 0.1) torch.cuda.synchronize(); t_bf = time.time() - t blk.bf16polish = 0 r_bf = (L.relax(blk, z_bf, xin, 1, 0.1) - z_bf).norm().item() zdb = ((z_bf - z_ref).norm() / (z_ref.norm() + 1e-12)).item() print(f"[{name}] bf16+20 : {t_bf:5.2f}s res={r_bf:.2e} z-diff={zdb:.2e}", flush=True) print("FASTFP_GATE_DONE", flush=True)