Files
esh-pfi-infrastructure/services/gen-seat-mixed-quant/bench/bench_heresy.json
T
vh 11b688ff68 feat(gen-seat): promote absolute-heresy to the live gen seat
MuXodious/Qwen3.8-27B-absolute-heresy (Heretic v1.4.0 + SOMPOA, trial T377,
pin c2374593) quantized through our mixed NVFP4+FP8 recipe and promoted after
passing the full gate on the probe port.

Gate vs incumbent -- MTP acceptance 47.2% (48.2%), decode 103.5 tok/s (96.4),
prefill 6618/5403 at 6.7k/27k (6334/5085), TTFT 27k 5.00s (5.31s), perplexity
6.910 (7.059, 2.1% better), surface 6/6, abliteration compliance 4/4. On our
battery-instruct arm -- the framing that actually elicits refusals -- 0/55 with
zero EMPTY, so no catatonia at the hard edge.

Speed deltas are image-confounded: the probe ran the seat's pinned nightly
while the incumbent's stored numbers came from an earlier image. Read as not
worse. Acceptance, perplexity, surface and refusal are apples-to-apples.

All 7 LiteLLM aliases verified end-to-end. GPU0 at 91.3/97.9 GB with meromero
healthy -- more headroom than the previous build. Incumbent weights untouched
and .env.bak-heresy-20260817 in place for rollback.

Candidate is a 2-day-old RC1 with ~348 downloads; watch real multi-turn use.
2026-08-17 17:23:35 -07:00

29 lines
644 B
JSON

{
"tag": "heresy",
"model": "probe",
"tok_s_median": 103.46655635565449,
"tok_s_mean": 102.60692862947714,
"tok_s_min": 90.30587796547803,
"tok_s_max": 115.13389586042238,
"mtp_accept_median": 0.47231349640988196,
"rates": [
103.09345339858122,
115.13389586042238,
98.90613513574037,
90.30587796547803,
96.87736392506643,
103.83965931272775,
108.24742296674285,
104.45162047105809
],
"accs": [
0.46987951807228917,
0.5698198198198198,
0.4373795761078998,
0.3719298245614035,
0.4218455743879473,
0.47474747474747475,
0.5084388185654009,
0.4796747967479675
]
}