diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-06 09:17:36 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-06 09:17:36 -0500 |
| commit | 9a8b2796ca12e4d4c24717485a635a301aa6d07f (patch) | |
| tree | 550c7a60705c6f02976da27b86184faaac70b891 /ep_run/runs/abl3_queue.sh | |
| parent | 488c50e1bdbf8f420b2ad5b4021a7f950d121835 (diff) | |
aggregate speed bench: speed tier hf+sd 1.47x; accuracy tier hf+sd+t80+avg (0.91x, cos 0.94, avg free); compile demoted
Full-ep_step wall times on quiet A6000 (warm s2000, B24), res parity across
all 8 configs. compile only 1.12x at this shape (historical 1.46x was a
different workload split); FULL cmp_sdpa saves 4% over eager at t80 — not
worth the guard complexity. tforce_sdpa added (flash baked into compiled
graph, flag-free so grad paths never see SDPA). bp_lm --tie probe in flight.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
Diffstat (limited to 'ep_run/runs/abl3_queue.sh')
0 files changed, 0 insertions, 0 deletions