Evidaxis

As of 2026-09-26: KTransformers (Inference & Serving) is under weekly measurement. Axis coverage: 1 of 3 axes measurable. Gate: not computable — 1 of 3 axes measurable

KTransformers

repo
Inference & Serving · n = 13 · kvcache-ai/ktransformers
1 of 3 axes measurable · conf low
convergence gate
Convergence gate: Gate: not computable — 1 of 3 axes measurable Development velocity: measured × Citation momentum: not measurable ∅ Direct-dependents momentum (deps.dev): not measurable ∅
gate
0 of 3 axes

Gate: not computable — 1 of 3 axes measurable

Gate: not computable — 1 of 3 axes measurable
position in cohort distribution one of 13 in cohort
percentile 8 within cohort p25 p50 p75 p0 p100
percentile
p8
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z-1.54 within cohort, log-slope -0.018/wk.0-1.54
velocity z
-1.54 σ
slope
-0.018/wk
log-slope -0.018/wk
citation z Citation axis: insufficient source coverage (source returned too few observations).
direct-dependents z Direct-dependents axis: minimum of 14 clean points and 5 latest dependents not met.
cohort
13
systems measured
weekly commits
4.3
Development velocity axis: measured.
total citations
n/a
Citation axis: insufficient source coverage (source returned too few observations).
momentum
30.7
percentile p8
commit heatmap, last 26 weeks4.3/wk
weekly commits, 26 weeks26 weeks of commits, peak 11 in a week, 23 active weeks, 122 total.week 1: 8 commitsweek 2: 5 commitsweek 3: 5 commitsweek 4: 8 commitsweek 5: 8 commitsweek 6: 10 commitsweek 7: 3 commitsweek 8: 3 commitsweek 9: 2 commitsweek 10: 2 commitsweek 11: 1 commitsweek 12: 7 commitsweek 13: 8 commitsweek 14: 0 commitsweek 15: 3 commitsweek 16: 3 commitsweek 17: 4 commitsweek 18: 0 commitsweek 19: 4 commitsweek 20: 0 commitsweek 21: 7 commitsweek 22: 6 commitsweek 23: 5 commitsweek 24: 11 commitsweek 25: 8 commitsweek 26: 1 commits
weeks
26
peak/wk
11
active
23
total
122
citations by yearCitation axis: insufficient source coverage (source returned too few observations).
Daily dependents count (unscored) 0 dependents 0 direct · pypi/ktransformers · deps.dev · the scored m3 axis uses weekly partitions

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 -4.21, regime recent slope sign differs from prior window. prior slope -0.023, recent slope +0.096 per week. -0.023prior 39w+0.096recent 13w-4.21×
swing
-4.21×
regime
recent slope sign differs from prior window
windows
13w vs 39w
snapshot 1 of 1 · · m3
commit-axis Sharpe log-linear slope over residual std, value -0.025 with 95% CI -0.050 to +0.001, 50 degrees of freedom. CI spans zero.0-0.02595% CI -0.050, +0.001-0.050+0.001
sharpe
-0.025
95% ci
-0.050, +0.001
dof
50
snapshot 1 of 1 · · m3
commit changepoint52 weekly commit points. Changepoint at week 7 (2025-11-15), slope change -5.598 commits per week.2025-11-15
date
week
7 of 52
Δslope
-5.598/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
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m3
methodology gate snapshot 1 of 1 · · m3
commit weeks
52
citation years
1
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

Reconstructed history

KTransformers reconstructed weekly commits47 points, range 1 to 29 commits/wk.
min
1 commits/wk
max
29 commits/wk
latest
8 commits/wk
points
47

Weekly commits over the past year, reconstructed from git history (GitHub commit_activity). This is reconstructed, not a point-in-time capture. Evidaxis captures the Type-2 signals (watchers, issues, dependents) live and never backfills them; those are the moat.

Daily dependents count (unscored)

KTransformers dependents over time13 points, range 0 to 0 dependents.
min
0 dependents
max
0 dependents
latest
0 dependents
points
13

Downstream packages depending on pypi/ktransformers (deps.dev), captured point-in-time each snapshot. This daily series is unscored. The scored axis in m3 uses weekly partitions.

Measurement states

KTransformers is under weekly measurement. History: 13 weekly observations; minimum 4. Development velocity axis: measured. Citation axis: insufficient source coverage (source returned too few observations). Direct-dependents axis: minimum of 14 clean points and 5 latest dependents not met. Gate: not computable — 1 of 3 axes measurable

Sources

kvcache-ai/ktransformers development-velocity axis
OpenAlex paper citation-momentum axis

Others in Inference & Serving

AIBrix Inference & Serving
1 of 3 axes measurable
59
p83
vel +0.71 cit no axis deps no axis
axis dials
+0.71 n/a n/a
llama.cpp Inference & Serving
2 of 3 axes measurable
50
p67
vel -0.17 cit no axis deps +0.22
axis dials
-0.17 n/a +0.22
llm-d Inference & Serving
1 of 3 axes measurable
37
p17
vel -1.08 cit no axis deps no axis
axis dials
-1.08 n/a n/a
LMCache Inference & Serving
1 of 3 axes measurable
50
p58
vel +0.01 cit no axis deps no axis
axis dials
+0.01 n/a n/a
LMDeploy Inference & Serving
1 of 3 axes measurable
50
p50
vel +0.00 cit no axis deps no axis
axis dials
+0.00 n/a n/a
Mooncake Inference & Serving
1 of 3 axes measurable
70
p100
vel +1.59 cit no axis deps no axis
axis dials
+1.59 n/a n/a

Full Inference & Serving cohort →

Direct-dependents momentum (deps.dev)

Direct-dependents axis: minimum of 14 clean points and 5 latest dependents not met.

Coverage state
below_floor
Cohort z
no axis
OLS slope
n/a
Theil-Sen slope
n/a
Latest direct dependents
1
Confirmed-clean points
2
Reconstructed history points
n/a
As-of partition
n/a
Fragility veto
n/a
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

Cite this measurement

Plain citation

Evidaxis. KTransformers measurement record. Snapshot 2026-09-26. https://evidaxis.org/e/e_MMGH765AVAA/ Concept DOI: 10.5281/zenodo.21076011.

BibTeX

@dataset{evidaxis_e_MMGH765AVAA_20260926,
  title = {KTransformers measurement record},
  publisher = {Evidaxis},
  year = {2026},
  url = {https://evidaxis.org/e/e_MMGH765AVAA/},
  doi = {10.5281/zenodo.21076011}
}

Download record (JSON)

entity_id e_MMGH765AVAA methodology m3 snapshot 9d2fe956adbc period 2026-w39 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m3, never edited by hand. Cite as: “Evidaxis, KTransformers, entity e_MMGH765AVAA, snapshot 2026-w39.”

Durable reference (format-independent): urn:evidaxis:claim:e_MMGH765AVAA:m3:2026-09-26