Evidaxis
Dated record

exllamav3

repo · turboderp-org/exllamav3 · paper: not linked · as of

Niche: not yet assigned.

56.2 commits per week averaged over the trailing window. No paper is linked in OpenAlex. Dependents: no reading in the scored panel. 1 of 4 weekly observations; full commit series captured. 1,524 GitHub stars, recorded, not scored. Measured 2026-09-26 for exllamav3; sources linked below.

commits/wk 56.2 averaged, trailing window last commit week 2026-09-20 measured · GitHub ·
citations no paper linked all years, indexed to date no reading · OpenAlex ·
direct dependents not in the scored panel partition 2026-09-26 no reading · deps.dev snapshot ·
stars 1,524 recorded, not scored measured · GitHub ·

Is exllamav3 still maintained?

56.2 commits per week averaged over the trailing window.

GitHub averaged 56.2 per week over the trailing window; raw weekly counts below are individual weeks.

Last commit week 2026-09-20.

Commits in the latest captured week vs 4 weeks earlier: 4 · vs 26 weeks earlier: 15 · 52-week range: 0 to 154 commits in an individual week.

line chart: exllamav3, weekly commits, 31 in latest week, 2025-09-28 to 2026-09-20
exllamav3 averaged 56.2 commits a week. GitHub commit_activity · .
Latest eight weeks
Week startingCommits
2026-08-0259
2026-08-0922
2026-08-1623
2026-08-2327
2026-08-30154
2026-09-0679
2026-09-1355
2026-09-2031
heatmap chart: exllamav3, weeks with commits, 26 of 26, 2026-03-29 to 2026-09-20
26 of the last 26 captured weeks had commits for exllamav3. GitHub commit_activity · .
All 52 weeks
Weekly commits
Week startingCommits
2025-09-286
2025-10-0513
2025-10-1213
2025-10-195
2025-10-2618
2025-11-021
2025-11-0933
2025-11-163
2025-11-236
2025-11-3011
2025-12-0711
2025-12-141
2025-12-216
2025-12-283
2026-01-048
2026-01-1110
2026-01-185
2026-01-251
2026-02-010
2026-02-086
2026-02-153
2026-02-224
2026-03-0144
2026-03-0817
2026-03-1510
2026-03-2216
2026-03-2916
2026-04-0528
2026-04-1229
2026-04-1920
2026-04-2641
2026-05-0329
2026-05-1036
2026-05-1725
2026-05-2425
2026-05-3121
2026-06-0716
2026-06-147
2026-06-214
2026-06-289
2026-07-0576
2026-07-1259
2026-07-1945
2026-07-2645
2026-08-0259
2026-08-0922
2026-08-1623
2026-08-2327
2026-08-30154
2026-09-0679
2026-09-1355
2026-09-2031

GitHub commit_activity · period 2025-09-28 to 2026-09-20 · n = 52 weeks · method weekly totals; reconstructed dates · updated · version 9d2fe956adbc-b1 · CSV

Readings

Recorded values and sources
ReadingValueΔ 4 weeksΔ 26 weeks52-week rangeInstrumentDateReproducePrevious reading
Commits per week56.223.545.94.8 to 56.2GitHub, trailing 12 weeks2026-09-26Public queryno reading
Citing worksno readingno readingno readingno readingOpenAlex, all years2026-09-26Public queryno reading
Direct dependentsno readingno readingno readingno readingDirect dependents2026-09-26Public queryno reading
Daily dependents (unscored)no readingno readingno readingno readingdeps.dev REST, unscored2026-09-26Public queryno reading
Stars1,524no readingno reading1,524 to 1,524GitHub stars, unscored2026-09-26Public queryno reading

Evidaxis snapshot · period 2026-09-26 · n = 1 system · method source linked readings · updated · version 9d2fe956adbc-b1

How to cite exllamav3's record?

Evidaxis. exllamav3 measurement record. Snapshot 2026-09-26. urn:evidaxis:claim:e_DHTPECNK9XP:m3:2026-09-26. CC0-1.0. https://evidaxis.org/e/e_DHTPECNK9XP/

Evidaxis · period 2026-09-26 · n = 1 system · method claim URN · updated · version 9d2fe956adbc-b1

What changed since the last snapshot?

No previous snapshot reading is available for this system.

slope chart: exllamav3, measured values, 2, 2026-09-26
First observation 2026-09-26 for exllamav3; 2 measured values. Evidaxis snapshots · .
Snapshot values
MetricPreviousCurrentDelta
Commits per weekno reading56.2no reading
Citing worksno readingno readingno reading
Direct dependentsno readingno readingno reading
Starsno reading1,524no reading

Evidaxis snapshots · period 2026-09-26 to 2026-09-26 · n = 1 partition · method paired snapshot values · updated · version 9d2fe956adbc-b1 · History CSV

Take the data or follow changes

Values and captured history are available under CC0-1.0. The system feed records changes to published numbers.

Evidaxis · period 2026-09-26 · n = 1 system · method CC0-1.0 open export · updated · version 9d2fe956adbc-b1

For teams tracking many systems

Use the cohort CSV, snapshot archive and membership manifest to reproduce observations across systems.

Cohort CSV · Snapshot archive · Membership manifest

Paper and links

Source records identify the system, repository and linked works; no paper authors are published.

What is not measured for exllamav3, and why

Missing readings describe instrument coverage. A missing value is not a measured zero.

Unmeasured slots
ReadingReason
Citing worksnot linked
Direct dependentsoutside panel
Daily dependents (unscored)no reading captured

Dependents: no reading in the scored panel.

Gate ETA: never published; Evidaxis makes no public actionable prediction.

Dependents ecosystem composition: no reading; this field is not present in the snapshot.

Evidaxis · period 2026-09-26 · n = 1 system · method measurement coverage · updated · version 9d2fe956adbc-b1

Measurement detail

Gate, gauges, percentile, derived signals and snapshot receipt

History: 1 of 4 weekly observations. Axis coverage: 1 of 3 axes measurable. Gate: not computable - history 1 of 4 weekly observations

1 of 4 weekly observations; full commit series captured.

exllamav3

repo
Unassigned (AI-v1 census) · n = 5778 · turboderp-org/exllamav3
1 of 3 axes measurable · conf low
convergence gate
Convergence gate: Gate: not computable - history 1 of 4 weekly observations Development velocity: rising vote Citation momentum: not measurable ∅ Direct-dependents momentum (deps.dev): not measurable ∅
gate
1 of 3 axes

Gate: not computable - history 1 of 4 weekly observations

· Evidaxis snapshot · 2026-09-26
Gate: not computable - history 1 of 4 weekly observations
position in cohort distribution one of 5778 in cohort
percentile 95 within cohort p25 p50 p75 p0 p100
percentile
p95
· Evidaxis snapshot · 2026-09-26
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z+3.01 within cohort, log-slope +0.036/wk.0+3.01
velocity z
+3.01 σ
slope
+0.036/wk
· Evidaxis snapshot · 2026-09-26
log-slope +0.036/wk
citation z Citation source: not measured.
direct-dependents z Direct-dependents axis: outside the frozen panel; not measured.
cohort
5778
systems measured
weekly commits
56.2
Development velocity axis: measured.
total citations
no reading
Citation source: not measured.
momentum
87.6
percentile p95
commit heatmap, last 26 weeks56.2/wk
weekly commits, 26 weeks26 weeks of commits, peak 154 in a week, 26 active weeks, 981 total.week 1: 16 commitsweek 2: 28 commitsweek 3: 29 commitsweek 4: 20 commitsweek 5: 41 commitsweek 6: 29 commitsweek 7: 36 commitsweek 8: 25 commitsweek 9: 25 commitsweek 10: 21 commitsweek 11: 16 commitsweek 12: 7 commitsweek 13: 4 commitsweek 14: 9 commitsweek 15: 76 commitsweek 16: 59 commitsweek 17: 45 commitsweek 18: 45 commitsweek 19: 59 commitsweek 20: 22 commitsweek 21: 23 commitsweek 22: 27 commitsweek 23: 154 commitsweek 24: 79 commitsweek 25: 55 commitsweek 26: 31 commits
weeks
26
peak/wk
154
active
26
total
981
· Evidaxis snapshot · 2026-09-26
citations by yearCitation source: not measured.
recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio +1.44, regime accelerating. prior slope +0.031, recent slope +0.045 per week. +0.031prior 39w+0.045recent 13w+1.44×
swing
+1.44×
regime
accelerating
windows
13w vs 39w
snapshot 1 of 1 · · m3
commit-axis Sharpe log-linear slope over residual std, value +0.053 with 95% CI +0.029 to +0.077, 50 degrees of freedom. CI excludes zero.0+0.05395% CI +0.029, +0.077+0.029+0.077
sharpe
+0.053
95% ci
+0.029, +0.077
dof
50
snapshot 1 of 1 · · m3
commit changepoint52 weekly commit points. Changepoint at week 49 (2026-09-05), slope change -40.017 commits per week.2026-09-05
date
week
49 of 52
Δslope
-40.017/wk
snapshot 1 of 1 · · m3
code-leads-citation lag reserved

reserved: citation series too short / axis absent for cross-correlation

status
reserved
value
insufficient data
snapshot 1 of 1 · · m3
axis alpha vs cohort reserved

reserved: cohort N too small for regression (power ~0)

status
reserved
value
insufficient data
snapshot 1 of 1 · · m3
methodology gate snapshot 1 of 1 · · m3
commit weeks
52
citation years
0
shipped
3
reserved
3

shipped

  • recency-swing
  • commit-sharpe
  • commit-changepoint

reserved

  • code-leads-citation-lag
  • axis-alpha
  • gate-eta
snapshot 1 of 1 · · m3

Direct-dependents momentum (deps.dev)

Direct-dependents axis: outside the frozen panel; not measured.

Coverage state
out_of_panel
Cohort z
no axis
OLS slope
no reading
Theil-Sen slope
no reading
Latest direct dependents
no reading
Confirmed-clean points
no reading
Reconstructed history points
no reading
As-of partition
no reading
Fragility veto
no reading
Rising vote
no

Source: deps.dev (Google), CC-BY 4.0. Modified: aggregated to system-level counts and momentum scores.

Axis definition · Snapshot axis correlations

Evidaxis · period 2026-09-26 · n = 1 system · method measurement detail · updated · version 9d2fe956adbc-b1 · record JSON · snapshot receipt