0515ad8ecc
Make telemetry audit replay-phase aware
2026-07-14 17:18:25 +08:00
791f7a8889
Audit telemetry intervention response for tuning
2026-07-14 16:39:38 +08:00
7a3631b528
Audit telemetry residual tuning premise
2026-07-14 15:44:37 +08:00
f01819680d
Report failed fidelity pilot gate
2026-07-14 13:57:12 +08:00
23142aa359
Strengthen fidelity calibration baseline
2026-07-14 13:08:45 +08:00
16239bef00
Add fidelity-aware verification pilot
2026-07-14 12:49:53 +08:00
57dd6a9fac
Record static-policy oracle gap refutation
2026-07-14 02:18:44 +08:00
16177b0045
Close shifted oracle frontier boundaries
2026-07-14 00:32:09 +08:00
0f891d99c9
Generalize oracle transport retry rule
2026-07-14 00:00:24 +08:00
d3bc63a972
Quarantine transport-invalid oracle trial
2026-07-13 23:16:04 +08:00
a9e7e9991e
Extend oracle gap P06 bracket
2026-07-13 22:21:17 +08:00
34e1f4c144
Add static-policy oracle gap experiment
2026-07-13 20:25:44 +08:00
a730b368d6
Document CollectiveSpec P2 no-go gate
2026-07-13 18:47:31 +08:00
5359463652
Record CollectiveSpec P0 no-go evidence
2026-07-13 18:11:32 +08:00
5ae0525611
Add window-scoped session closure fallback
2026-07-13 16:23:38 +08:00
eb67212b17
Tighten CollectiveSpec system research gates
2026-07-13 16:05:43 +08:00
9b3a2eab80
Add reproducible CollectiveSpec opportunity screen
2026-07-13 15:09:01 +08:00
6db7308558
Add SimFid+OpProf campaign overview
...
Entry-point summary of both closed campaigns: verdicts, corrected
readings (P5 supersedes P3's P10-vs-P04 magnitude), methodological
findings (co-location SLO validity, arrival uniformization, compile-
factor env poisoning), artifact map, and GPU accounting.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-07-13 11:06:12 +08:00
46d15f0e13
Add simulator fidelity review of Frontier baseline
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-07-13 11:06:11 +08:00
d5b276180d
Add OpProf campaign: protocols, results, patches, run evidence (P0-P6)
...
Workload-conditioned operator profiling on patched vLLM 0.24.0 +
Qwen3-30B-A3B/H20. H1b PASS (irregular patterns carry +23-45pp R64
raggedness, 8-45% token-efficiency loss vs rectangular controls);
mechanism decomposition kills the padding narrative and finds the
arrival-uniformization artifact (-12.9%); cross-version churn surface
shows TP2/MNS64 -29.4% across vLLM 0.20->0.24 while the argmax held.
Raw Layer-1 JSONL streams (507 MB) stay on disk, git-ignored; footer
sidecars and metrics are tracked.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-07-13 11:06:10 +08:00
7ba98b6087
Add knob conditional effect figures
2026-07-06 13:19:09 +08:00
cb89549334
Add MaaS collaboration overview
2026-07-06 13:19:00 +08:00
adb5356c4b
Add advisory harness attribution and descriptor planner MVP
2026-06-30 12:05:03 +08:00
08429e5da8
Refine harness design flow overview
2026-06-29 20:41:54 +08:00
00ba573631
Document harness design contract
2026-06-29 20:26:58 +08:00
6c84dc91d7
Document hardened topology feedback
2026-06-29 02:34:12 +08:00
1c4ed4cab3
Document hardened harness feedback
2026-06-29 02:28:30 +08:00
6b25d56c1f
Gate GMU climb on measured improvement
2026-06-29 02:00:41 +08:00
ee101a7c24
Harden prefill scheduler harness
2026-06-29 01:54:02 +08:00
bfd85793f3
Prioritize uncovered prefill scheduler candidates
2026-06-29 01:30:34 +08:00
36c301c128
Add normalized prefill scheduler harness
2026-06-29 01:12:19 +08:00
bef260f183
Document bad-start robustness suite
2026-06-26 22:19:46 +08:00
2937539b49
Persist harness candidate set snapshots
2026-06-26 22:17:47 +08:00
5080b50315
Veto repeated materialized configs
2026-06-26 22:15:47 +08:00
825d3e03e9
Add harness candidate set audit
2026-06-26 22:02:09 +08:00
42f75553a6
Document full config signature validation
2026-06-26 21:52:18 +08:00
7f50b8b8ea
Document bad-start validation results
2026-06-26 20:50:20 +08:00
95ad124a1b
Document auto search high policy
2026-06-26 19:53:30 +08:00
384cb58f1f
Add declarative harness prototype
2026-06-26 18:07:02 +08:00
4075c7abf0
Design declarative intervention harness
2026-06-26 17:15:06 +08:00
92eb186006
Add bad-start harness recovery planning
2026-06-26 16:44:24 +08:00
ce36cd79af
Document no-LLM harness mechanism
2026-06-25 10:32:29 +08:00
d85572e7b5
Update AITuner roadmap framing
2026-06-24 11:45:42 +08:00
c0a9235b80
Document vLLM-first harness roadmap
2026-06-24 11:23:39 +08:00
6d874ecbff
Update Qwen235B progress snapshot
2026-06-23 18:24:57 +08:00
403ae2e2b7
Document Qwen235B 2x2 progress
2026-06-23 18:23:56 +08:00
861d754f29
Localize Qwen27B harness ablation doc
2026-06-23 18:14:35 +08:00
76ec19224c
Document Qwen27B 2x2 harness ablation
2026-06-23 10:08:46 +08:00
816765071f
Complete harness-vs-naive ablation: harness 3x faster + stops; naive nondeterministic
...
Full naive run (dash1) reached the same TP4=0.34 optimum as the harness but took 6
iters (vs 2), never stopped (full budget), and spent trials 2-5 on worse TP2+runtime
detours. The other naive run (dash0) wandered runtime-only on TP1, found nothing, and
crashed the engine. Refined conclusion (matches paper §7.3): a strong model can
sometimes find the right knob unaided, so the harness's value is reliability + speed +
stop discipline, not that naive always fails. Harness: 2 iters-to-best, stopped at 4,
no regression. Naive: 3x slower at best, no stop, failed at worst.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com >
2026-06-17 13:03:26 +08:00
8e58b4033d
Note dash1 lacks LLM gateway access (naive-completion deferred to dash0)
...
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com >
2026-06-17 09:55:39 +08:00
