diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-16 07:32:45 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-16 07:32:45 -0500 |
| commit | 971c6c1e8d7866457ec12be9d678bb886d5cedf3 (patch) | |
| tree | d54666eacbd85bbce7acecdb9d88e187847bbd50 /docs/campaign/CASCADE_ABLATION_PLAN.md | |
| parent | 35e7582287ab5a82bf57561895b5a095dc9b6e24 (diff) | |
RESULT 30: quantization Delta-vs-Delta — zero-tax at 8-bit operating point for BOTH; EP-specific tax (1.4-8x) below it; beta-buyback prediction designed
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
Diffstat (limited to 'docs/campaign/CASCADE_ABLATION_PLAN.md')
| -rw-r--r-- | docs/campaign/CASCADE_ABLATION_PLAN.md | 24 |
1 files changed, 24 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md index 1502ed2..22d836f 100644 --- a/docs/campaign/CASCADE_ABLATION_PLAN.md +++ b/docs/campaign/CASCADE_ABLATION_PLAN.md @@ -568,6 +568,30 @@ direction), not training-under-fault; wave-2 = co-training with faults injected +### RESULT 30 (2026-07-16): QUANTIZATION Delta-vs-Delta MATRIX — equal at the operating point, EP-SPECIFIC tax below it. +BP mirror suite complete (bp_qctl baseline 1.2171 — resumed-tail+amp beats the original fp32 twin, +which is exactly why in-family baselines were required; user's methodology point vindicated). +| injection | Delta_EP (vs 1.2678) | Delta_BP (vs 1.2171) | EP/BP ratio | +|---|---|---|---| +| qup 10-bit | +0.012 | +0.003 | ~4x | +| qup 8-bit | +0.042 | +0.015 | ~3x | +| qup 6-bit | +0.092 | +0.068 | ~1.4x | +| qcomp 8-bit | **+0.002** | **+0.000** | **both ZERO** | +| qcomp 6-bit | +0.035 | +0.004 | ~8x | +| qcomp 4-bit | +0.140 | +0.061 | ~2.3x | +Readings: +1. AT THE T64 OPERATING POINT (8-bit compute + digital master): quantization is free for BOTH. + The BP QAT toolbox transfers AT this point; T64 green light unconditional on this axis. +2. BELOW it, the tax is EP-SPECIFIC (1.4-8x faster degradation): quantization roughness enters the + finite-beta measurement chain as an extra epsilon in the wall-1 SNR term (the estimator protects + an O(beta)-scale signal; BP has no such small signal). A blanket "EP inherits BP quantization + behavior" claim is REFUTED below 8 bits — publishable Stage-0 finding. +3. MECHANISM PREDICTION (designed, pending GPU): bigger beta should buy back quantization + tolerance (noise-to-displacement ratio ~ 1/beta) — one arm: qcomp6 + beta 1e-2 tail vs qcomp6@3e-3 + (+0.035). If confirmed, the window story absorbs quantization as another epsilon term. +4. Procurement consequence: acceptance ENOB bar STAYS ~7 (do NOT relax to 6 on BP intuition — + EP@6-bit compute is +0.035 real). + ### RESULT 29 (2026-07-16): qcomp VERDICT — 8-bit COMPUTE quantization is FREE (T64 green light); centmirror ships (1.39x). qcomp arms (compute on DAC-grid weights, fp32 master = word-streaming / shadow accumulation), same protocol, vs ctl 1.2678: |