<feed xmlns='http://www.w3.org/2005/Atom'>
<title>ept.git/ep_run/bp_lm.py, branch master</title>
<subtitle>Unnamed repository; edit this file 'description' to name the repository.
</subtitle>
<link rel='alternate' type='text/html' href='https://git.blackhao.com/ept.git/'/>
<entry>
<title>aggregate speed bench: speed tier hf+sd 1.47x; accuracy tier hf+sd+t80+avg (0.91x, cos 0.94, avg free); compile demoted</title>
<updated>2026-07-06T14:17:36+00:00</updated>
<author>
<name>Yuren Hao</name>
<email>yurenh2@illinois.edu</email>
</author>
<published>2026-07-06T14:17:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.blackhao.com/ept.git/commit/?id=9a8b2796ca12e4d4c24717485a635a301aa6d07f'/>
<id>9a8b2796ca12e4d4c24717485a635a301aa6d07f</id>
<content type='text'>
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 &lt;noreply@anthropic.com&gt;
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
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 &lt;noreply@anthropic.com&gt;
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
</pre>
</div>
</content>
</entry>
<entry>
<title>--holoavg shipped (gate 0.913-&gt;0.936 @t2sel160, batch2 +0.051) + farm wave-2 tooling</title>
<updated>2026-07-06T12:15:30+00:00</updated>
<author>
<name>Yuren Hao</name>
<email>yurenh2@illinois.edu</email>
</author>
<published>2026-07-06T12:15:30+00:00</published>
<link rel='alternate' type='text/html' href='https://git.blackhao.com/ept.git/commit/?id=488c50e1bdbf8f420b2ad5b4021a7f950d121835'/>
<id>488c50e1bdbf8f420b2ad5b4021a7f950d121835</id>
<content type='text'>
trend-aware stop + plateau averaging recovers the semi-convergence victims
exactly as predicted. Estimator pack now: holofast+sdpa+t2sel80(+holoavg).
Also: bp_lm stdinit/beta2/sched flags (anchor archaeology), dipfarm_freezer,
staged tol_sweep.sh (gated on hr2 verdict), bp_sweep.sh.

Co-Authored-By: Claude Fable 5 &lt;noreply@anthropic.com&gt;
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
trend-aware stop + plateau averaging recovers the semi-convergence victims
exactly as predicted. Estimator pack now: holofast+sdpa+t2sel80(+holoavg).
Also: bp_lm stdinit/beta2/sched flags (anchor archaeology), dipfarm_freezer,
staged tol_sweep.sh (gated on hr2 verdict), bp_sweep.sh.

Co-Authored-By: Claude Fable 5 &lt;noreply@anthropic.com&gt;
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
</pre>
</div>
</content>
</entry>
<entry>
<title>bp_lm twin control + env forensics probes + holo_a_track_avg (semi-convergence fix, ungated)</title>
<updated>2026-07-06T07:22:54+00:00</updated>
<author>
<name>Yuren Hao</name>
<email>yurenh2@illinois.edu</email>
</author>
<published>2026-07-06T07:22:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.blackhao.com/ept.git/commit/?id=8f43de671cf03ee20d5d652b6cd3ba575982a436'/>
<id>8f43de671cf03ee20d5d652b6cd3ba575982a436</id>
<content type='text'>
BP+EMA 2x2 (local, healthy env): qknorm {1.9951, 1.9977}, no-qknorm {1.9728,
1.9732} -&gt; parameterization-matched BP twin tops at ~1.97 vs EP 1.7888: the
equilibrium computation's iteration/depth dividend = 0.18 CE from identical
parameters. External anchor (tuned depth-1 BP, 1.7921): EP at parity.
bp_lm on 107/2.3.1 gave 1.9823 ~= local -&gt; plain backward exonerated on the
pascal env; the 107 divergence (pair/floss/resreg dead by step 600) narrows
to the EP reg/estimator loop. Single-step fingerprints all match (a/b/c/d) -&gt;
suspected intermittent kernel issue; discriminators in flight (torch-2.7 env
probe + delay_hr2's step-2000 reg-on transition).

Co-Authored-By: Claude Fable 5 &lt;noreply@anthropic.com&gt;
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
BP+EMA 2x2 (local, healthy env): qknorm {1.9951, 1.9977}, no-qknorm {1.9728,
1.9732} -&gt; parameterization-matched BP twin tops at ~1.97 vs EP 1.7888: the
equilibrium computation's iteration/depth dividend = 0.18 CE from identical
parameters. External anchor (tuned depth-1 BP, 1.7921): EP at parity.
bp_lm on 107/2.3.1 gave 1.9823 ~= local -&gt; plain backward exonerated on the
pascal env; the 107 divergence (pair/floss/resreg dead by step 600) narrows
to the EP reg/estimator loop. Single-step fingerprints all match (a/b/c/d) -&gt;
suspected intermittent kernel issue; discriminators in flight (torch-2.7 env
probe + delay_hr2's step-2000 reg-on transition).

Co-Authored-By: Claude Fable 5 &lt;noreply@anthropic.com&gt;
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
</pre>
</div>
</content>
</entry>
</feed>
