Evidaxis

As of 2026-11-07: TensorRT-LLM (Inference & Serving) is under weekly measurement. Axis coverage: 1 of 3 axes measurable. Gate: not computable — 1 of 3 axes measurable

TensorRT-LLM

repo
Inference & Serving · n = 14 · NVIDIA/TensorRT-LLM
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 14 in cohort
percentile 38 within cohort p25 p50 p75 p0 p100
percentile
p38
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z-0.38 within cohort, log-slope +0.011/wk.0-0.38
velocity z
-0.38 σ
slope
+0.011/wk
log-slope +0.011/wk
citation z Citation source: not measured.
direct-dependents z Direct-dependents axis: minimum of 14 usable points of the new quantity and 5 latest dependents not met.
cohort
14
systems measured
weekly commits
212.8
Development velocity axis: measured.
total citations
n/a
Citation source: not measured.
momentum
45.2
percentile p38
commit heatmap, last 26 weeks212.8/wk
weekly commits, 26 weeks26 weeks of commits, peak 285 in a week, 26 active weeks, 5044 total.week 1: 185 commitsweek 2: 167 commitsweek 3: 176 commitsweek 4: 177 commitsweek 5: 182 commitsweek 6: 85 commitsweek 7: 156 commitsweek 8: 180 commitsweek 9: 195 commitsweek 10: 195 commitsweek 11: 190 commitsweek 12: 187 commitsweek 13: 197 commitsweek 14: 219 commitsweek 15: 225 commitsweek 16: 260 commitsweek 17: 248 commitsweek 18: 229 commitsweek 19: 254 commitsweek 20: 146 commitsweek 21: 105 commitsweek 22: 120 commitsweek 23: 208 commitsweek 24: 212 commitsweek 25: 285 commitsweek 26: 261 commits
weeks
26
peak/wk
285
active
26
total
5044
citations by yearCitation source: not measured.
Daily dependents count (unscored) 0 dependents 0 direct · pypi/tensorrt-llm · deps.dev · the scored m5 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 -0.60, regime recent slope sign differs from prior window. prior slope +0.012, recent slope -0.007 per week. +0.012prior 39w-0.007recent 13w-0.60×
swing
-0.60×
regime
recent slope sign differs from prior window
windows
13w vs 39w
snapshot 1 of 1 · · m5
commit-axis Sharpe log-linear slope over residual std, value +0.050 with 95% CI +0.024 to +0.076, 50 degrees of freedom. CI excludes zero.0+0.05095% CI +0.024, +0.076+0.024+0.076
sharpe
+0.050
95% ci
+0.024, +0.076
dof
50
snapshot 1 of 1 · · m5
commit changepoint52 weekly commit points. Changepoint at week 47 (2026-10-03), slope change +34.123 commits per week.2026-10-03
date
week
47 of 52
Δslope
+34.123/wk
snapshot 1 of 1 · · m5
code-leads-citation lag reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m5
axis alpha vs cohort reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m5
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m5
methodology gate snapshot 1 of 1 · · m5
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 · · m5

Daily dependents count (unscored)

TensorRT-LLM dependents over time19 points, range 0 to 0 dependents.
min
0 dependents
max
0 dependents
latest
0 dependents
points
19

Downstream packages depending on pypi/tensorrt-llm (deps.dev), captured point-in-time each snapshot. This daily series is unscored. The scored axis in m5 uses weekly partitions.

Measurement states

TensorRT-LLM is under weekly measurement. History: 16 weekly observations; minimum 4. Development velocity axis: measured. Citation source: not measured. Direct-dependents axis: minimum of 14 usable points of the new quantity and 5 latest dependents not met. Gate: not computable — 1 of 3 axes measurable

Sources

NVIDIA/TensorRT-LLM development-velocity axis

Others in Inference & Serving

AIBrix Inference & Serving
1 of 3 axes measurable
58
p85
vel +0.66 cit no axis deps no axis
axis dials
+0.66 n/a n/a
FlashInfer Inference & Serving
2 of 3 axes measurable
63
p100
vel +2.70 cit no axis deps -0.67
axis dials
+2.70 n/a -0.67
KTransformers Inference & Serving
1 of 3 axes measurable
42
p23
vel -0.66 cit no axis deps no axis
axis dials
-0.66 n/a n/a
llama.cpp Inference & Serving
2 of 3 axes measurable
55
p77
vel +0.01 cit no axis deps +0.77
axis dials
+0.01 n/a +0.77
llm-d Inference & Serving
1 of 3 axes measurable
41
p8
vel -0.73 cit no axis deps no axis
axis dials
-0.73 n/a n/a
LMCache Inference & Serving
1 of 3 axes measurable
49
p46
vel -0.11 cit no axis deps no axis
axis dials
-0.11 n/a n/a

Full Inference & Serving cohort →

Direct-dependents momentum (deps.dev)

Direct-dependents axis: minimum of 14 usable points of the new quantity 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
0
Confirmed-clean points
29
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. TensorRT-LLM measurement record. Snapshot 2026-11-07. https://evidaxis.org/e/e_9SWWW2SWASG/ Concept DOI: 10.5281/zenodo.21076011.

BibTeX

@dataset{evidaxis_e_9SWWW2SWASG_20261107,
  title = {TensorRT-LLM measurement record},
  publisher = {Evidaxis},
  year = {2026},
  url = {https://evidaxis.org/e/e_9SWWW2SWASG/},
  doi = {10.5281/zenodo.21076011}
}

Download record (JSON)

entity_id e_9SWWW2SWASG methodology m5 snapshot 868e3c39d9c7 period 2026-w45 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m5, never edited by hand. Cite as: “Evidaxis, TensorRT-LLM, entity e_9SWWW2SWASG, snapshot 2026-w45.”

Durable reference (format-independent): urn:evidaxis:claim:e_9SWWW2SWASG:m5:2026-11-07