Evidaxis

vLLM

repo incumbent
Inference & Serving · n = 13 · vllm-project/vllm
Calibration · conf low
momentum
momentum 58.8 of 100 58.8 /100
momentum
58.8/100
pctile
p92
convergence gate
Convergence gate: gate shut × ×
gate
0 of 2 axes

gate shut.

gate shut
position in cohort distribution one of 13 in cohort
percentile 92 within cohort p25 p50 p75 p0 p100
percentile
p92
momentum is the combined velocity and citation signal, percentile within cohort
velocity z
velocity z gaugevelocity z+0.70 within cohort, log-slope +0.023/wk.0+0.70
velocity z
+0.70 σ
slope
+0.023/wk
log-slope +0.023/wk
convergence planefull gate = rising
vLLM on the convergence plane vLLM at velocity z +0.70 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
+0.70
citation z
no axis
peers
12

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

citation z log-slope +2.043/yr
cohort
13
systems measured
weekly commits
397.9
not rising
total citations
1,238
present
momentum
58.8
percentile p92
commit heatmap, last 26 weeks397.9/wk
weekly commits, 26 weeks26 weeks of commits, peak 570 in a week, 26 active weeks, 8796 total.week 1: 261 commitsweek 2: 223 commitsweek 3: 322 commitsweek 4: 310 commitsweek 5: 330 commitsweek 6: 328 commitsweek 7: 254 commitsweek 8: 257 commitsweek 9: 239 commitsweek 10: 344 commitsweek 11: 289 commitsweek 12: 275 commitsweek 13: 260 commitsweek 14: 329 commitsweek 15: 312 commitsweek 16: 288 commitsweek 17: 294 commitsweek 18: 384 commitsweek 19: 364 commitsweek 20: 505 commitsweek 21: 369 commitsweek 22: 420 commitsweek 23: 428 commitsweek 24: 402 commitsweek 25: 570 commitsweek 26: 439 commits
weeks
26
peak/wk
570
active
26
total
8796
citations by yeartotal 1,238
Citations by year2023: 9, 2024: 163, 2025: 594, 2026: 472. Total 1238 citations.2023: 9 citations2392024: 163 citations241632025: 594 citations255942026: 472 citations26472
total cites
1238
years
4
latest yr
472
adoption 130 dependents 128 direct, 2 indirect · pypi/vllm · deps.dev · adoption signal, not part of the momentum score

vLLM holds an Evidaxis momentum score of 58.8 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 -379.83, regime reversing. prior slope -0.000, recent slope +0.041 per week. -0.000prior 39w+0.041recent 13w-379.83×
swing
-379.83×
regime
reversing
windows
13w vs 39w
snapshot 1 of 1 · · m2
commit-axis Sharpe log-linear slope over residual std, value +0.031 with 95% CI +0.007 to +0.055, 50 degrees of freedom. CI excludes zero.0+0.03195% CI +0.007, +0.055+0.007+0.055
sharpe
+0.031
95% ci
+0.007, +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
4
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

Adoption trend

vLLM dependents over time5 points, range 129 to 135 dependents.
min
129 dependents
max
135 dependents
latest
130 dependents
points
5

Downstream packages depending on pypi/vllm (deps.dev), captured point-in-time each snapshot. An adoption signal, not part of the momentum score.

Verdict

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

Sources

vllm-project/vllm development-velocity axis
OpenAlex paper citation-momentum axis
vllm.ai homepage

Embed this badge

Evidaxis calibration, vLLM
[![Evidaxis: vLLM](https://evidaxis.org/badge/e_R372CCSVG44/2026-w32.svg)](https://evidaxis.org/e/e_R372CCSVG44)

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
llama.cpp Inference & Serving
Calibration
51
p58
vel +0.07 cit no axis
axis dials
+0.07 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

Full Inference & Serving cohort →

entity_id e_R372CCSVG44 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, vLLM, entity e_R372CCSVG44, snapshot 2026-w32.”

Durable reference (format-independent): urn:evidaxis:claim:e_R372CCSVG44:m2:2026-08-08