Commit graph

12 commits

Author SHA1 Message Date
PeterChrz
7e57fb5e16
Split band total into Devlogic and Sysops; remove config badge
Replace the single Band total with two adjacent metric groups:
- Devlogic total: softbench, prosebench, psychbench, depthsweep
  (all non-infra, non-scenario suites)
- Sysops total: infrabench + scenariobench

Each group independently shows geo-mean tok/s, total tokens, and
pass/fail counts. Scenariobench contributes per-observation
gen_tokens/wall rates to the sysops geo-mean.

Remove the server-config badge (e.g. 'llama.cpp DFlash spec-decode,
131k ctx, fa on') from the front-page card header. Label, quant, and
engine badges remain.

Migration drops the old total_* columns and adds devlogic_* and
sysops_* columns to session_summaries.
2026-10-04 23:38:13 -04:00
PeterChrz
8c9e512fc2
Add geometric-mean band total (tok/s + tokens) under each band header 2026-09-30 15:47:01 -04:00
PeterChrz
9f9327bb27
v2.3: group runs by actual harness config, per-level depthsweep, scenario gen speed, named server configs 2026-09-19 23:45:04 -04:00
PeterChrz
3695632e58
v2.2: depthsweep suite (table, model, registry, run-detail branch), band column headers, GpuSeeder in DatabaseSeeder, device-flow + catalog + confirm-picker tests 2026-09-19 21:11:20 -04:00
PeterChrz
646cecc403
Device flow: one-time plaintext token pickup (plain_token stash), poll throttle 120/min for 3s CLI rhythm 2026-09-19 21:06:20 -04:00
PeterChrz
e406b52a2d
CLI device login flow (Sanctum + device_codes, authorize screen, /api/me, /api/gpus) + canonical GPU catalog (gpus table, seeder, import normalizer, my-runs confirm picker, festbench:gpus + festbench:tokens) 2026-09-19 12:56:40 -04:00
PeterChrz
2e205ef792
v2.1: session-grouped summary home page (GPU/model/quant/runner bands, per-suite pass/fail, avg + weighted tok/s), flat task table moved to /results, summary command + tables on schedule and after import 2026-09-18 20:12:30 -04:00
PeterChrz
11e720f6f3
v2 Phase D: home_snapshot table + refresh command, TTL caching, public CDN cache headers for guest pages 2026-09-18 15:01:41 -04:00
PeterChrz
72cde51978
v2 Phase C: suite-aware home table via all_results view, tailored run detail, per-suite tests 2026-09-18 14:49:09 -04:00
PeterChrz
8c75db59f0
v2 Phase A+B: Postgres, partitioned per-suite tables, suite registry, all_results view, import rework, surgical re-import of deterministic session 2026-09-18 14:41:33 -04:00
PeterChrz
49033c2456
Phase 2: benchmark_runs + run_results schema, models with visibility scope and immutability guard, factories, tests 2026-09-16 22:34:43 -04:00
PeterChrz
6d3675113d
Initial commit: Laravel 12 livewire-starter-kit + flux-pro, fortify, spatie/laravel-data 2026-09-16 22:28:11 -04:00