Evidaxis

llama.cpp

repo incumbent
Inference & Serving · n = 13 · ggml-org/llama.cpp
Calibration · conf low
momentum
momentum 50.9 of 100 50.9 /100
momentum
50.9/100
pctile
p58
convergence gate
Convergence gate: velocity only, citation axis absent × ∅
gate
0 of 2 axes

velocity only, citation axis absent.

gate shut
position in cohort distribution one of 13 in cohort
percentile 58 within cohort p25 p50 p75 p0 p100
percentile
p58
momentum is the combined velocity and citation signal, percentile within cohort
velocity z
velocity z gaugevelocity z+0.07 within cohort, log-slope +0.003/wk.0+0.07
velocity z
+0.07 σ
slope
+0.003/wk
log-slope +0.003/wk
convergence planefull gate = rising
llama.cpp on the convergence plane llama.cpp at velocity z +0.07 and citation z no axis, against 0 dual-axis cohort peers. single-axis: citation axis absent, excluded from the plane. z>=1 median velocity z → citation z ↑
velocity z
+0.07
citation z
no axis
peers
12

single-axis: citation axis absent, excluded from the plane.

citation z no citation axis
cohort
13
systems measured
weekly commits
112.8
not rising
total citations
n/a
no axis
momentum
50.9
percentile p58
commit heatmap, last 26 weeks112.8/wk
weekly commits, 26 weeks26 weeks of commits, peak 157 in a week, 26 active weeks, 2853 total.week 1: 107 commitsweek 2: 87 commitsweek 3: 66 commitsweek 4: 65 commitsweek 5: 156 commitsweek 6: 142 commitsweek 7: 131 commitsweek 8: 117 commitsweek 9: 117 commitsweek 10: 88 commitsweek 11: 115 commitsweek 12: 88 commitsweek 13: 105 commitsweek 14: 116 commitsweek 15: 129 commitsweek 16: 157 commitsweek 17: 124 commitsweek 18: 99 commitsweek 19: 129 commitsweek 20: 98 commitsweek 21: 57 commitsweek 22: 135 commitsweek 23: 109 commitsweek 24: 71 commitsweek 25: 121 commitsweek 26: 124 commits
weeks
26
peak/wk
157
active
26
total
2853
citations by yearno axis

llama.cpp holds an Evidaxis momentum score of 50.9 of 100 on methodology m2, snapshot 2026-08-08, measured within the Inference & Serving cohort (n = 13). It is a mature incumbent included to calibrate the cohort, measured but not gate-eligible.

Derived signals

second-order reads, computed from the published series

Three signals ship when the commit series is statistically sufficient; the rest are held in a reserved state until the data supports them. A reserved signal shows its reason, never a fabricated number. How these are computed.

recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio -2.04, regime reversing. prior slope +0.010, recent slope -0.020 per week. +0.010prior 39w-0.020recent 13w-2.04×
swing
-2.04×
regime
reversing
windows
13w vs 39w
snapshot 1 of 1 · · m2
commit-axis Sharpe log-linear slope over residual std, value +0.035 with 95% CI +0.015 to +0.055, 50 degrees of freedom. CI excludes zero.0+0.03595% CI +0.015, +0.055+0.015+0.055
sharpe
+0.035
95% ci
+0.015, +0.055
dof
50
snapshot 1 of 1 · · m2
commit changepoint52 weekly commit points. No significant changepoint detected (|delta slope| within the noise floor).no significant changepoint
changepoint
none detected
snapshot 1 of 1 · · m2
code-leads-citation lag reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m2
axis alpha vs cohort reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m2
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m2
methodology gate snapshot 1 of 1 · · m2
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 · · m2

Verdict

llama.cpp is a mature incumbent included to calibrate its cohort. It is measured but not badge-eligible.

Sources

ggml-org/llama.cpp development-velocity axis

Embed this badge

Evidaxis calibration, llama.cpp
[![Evidaxis: llama.cpp](https://evidaxis.org/badge/e_Z7YDNC4F139/2026-w32.svg)](https://evidaxis.org/e/e_Z7YDNC4F139)

Others in Inference & Serving

AIBrix Inference & Serving
Single-axis
52
p67
vel +0.15 cit no axis
axis dials
+0.15 n/a
KTransformers Inference & Serving
Single-axis
36
p8
vel -1.12 cit no axis
axis dials
-1.12 n/a
llm-d Inference & Serving
Single-axis
37
p17
vel -1.01 cit no axis
axis dials
-1.01 n/a
LMCache Inference & Serving
Single-axis
51
p50
vel +0.04 cit no axis
axis dials
+0.04 n/a
LMDeploy Inference & Serving
Single-axis
46
p33
vel -0.34 cit no axis
axis dials
-0.34 n/a
Mooncake Inference & Serving
Watch
63
p100
vel +1.05 cit no axis
axis dials
+1.05 n/a

Full Inference & Serving cohort →

entity_id e_Z7YDNC4F139 methodology m2 snapshot 035a72a81e59 period 2026-w32 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m2, never edited by hand. Cite as: “Evidaxis, llama.cpp, entity e_Z7YDNC4F139, snapshot 2026-w32.”

Durable reference (format-independent): urn:evidaxis:claim:e_Z7YDNC4F139:m2:2026-08-08