ept.git/ep_run/sdpa_gate.py, branch xiang Unnamed repository; edit this file 'description' to name the repository. --sdpa: fused flash attention in the no_grad relax loop — 1.45x free phase, z* parity 4e-7 2026-07-05T10:09:36+00:00 Yuren Hao yurenh2@illinois.edu 2026-07-05T10:09:36+00:00 75ff326dcb40cd960abd56e9c9c18a45d9e5e2c2 Scoped via blk._sdpa set only inside relax()'s loop (grad paths jvp/vjp/resreg keep the manual attention: no forward-mode-through-flash risk). Combined with --holofast: ~1.51x full-step exact-math tier. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn 
Scoped via blk._sdpa set only inside relax()'s loop (grad paths jvp/vjp/resreg
keep the manual attention: no forward-mode-through-flash risk). Combined with
--holofast: ~1.51x full-step exact-math tier.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn