Evidaxis
Dated record

LMCache

repo · Inference & Serving, n = 13 · LMCache/LMCache · paper: W4417150458 · as of

40.2 commits/week averaged over the trailing window (niche median 32). OpenAlex: 2 citing works; fewer than 3 completed years. deps.dev: 3 direct dependents, below the 5-dependent floor. 11,912 GitHub stars, recorded, not scored. Measured 2026-09-26 for LMCache; sources linked below.

commits/wk 40.2 averaged, trailing window niche median 32 (n = 13) last commit week 2026-09-20 measured · GitHub ·
citations 2 all years, indexed to date niche median 13 (n = 5) measured · OpenAlex ·
direct dependents 3 partition 2026-09-26 niche median 8 (n = 8) measured · deps.dev snapshot ·
stars 11,912 recorded, not scored niche median 14,719 (n = 13) measured · GitHub ·

Is LMCache still maintained?

Development velocity is the one measurable axis of three: 40.2 commits per week averaged over the trailing window (niche median 32/wk, n = 13).

GitHub averaged 40.2 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: 10 · vs 26 weeks earlier: 12 · 52-week range: 6 to 62 commits in an individual week.

line chart: LMCache, weekly commits, 53 in latest week vs niche median 44, 2025-09-28 to 2026-09-20
LMCache averaged 40.2 commits a week, 1.3 times the niche median of 32. GitHub commit_activity · .
Latest eight weeks
Week startingCommitsNiche P25Niche P75
2026-08-023415128
2026-08-093820167
2026-08-163319160
2026-08-234311125
2026-08-304825141
2026-09-063224135
2026-09-135223140
2026-09-205315138
heatmap chart: LMCache, weeks with commits, 26 of 26, 2026-03-29 to 2026-09-20
26 of the last 26 captured weeks had commits for LMCache. GitHub commit_activity · .
All 52 weeks
Weekly commits
Week startingCommits
2025-09-2822
2025-10-0513
2025-10-1217
2025-10-1920
2025-10-2619
2025-11-0223
2025-11-0916
2025-11-1637
2025-11-2329
2025-11-3031
2025-12-0723
2025-12-1423
2025-12-216
2025-12-2814
2026-01-0424
2026-01-1120
2026-01-1823
2026-01-2512
2026-02-0117
2026-02-0818
2026-02-1518
2026-02-2222
2026-03-0123
2026-03-0834
2026-03-1523
2026-03-2241
2026-03-2925
2026-04-0519
2026-04-1236
2026-04-1947
2026-04-2619
2026-05-0339
2026-05-1036
2026-05-1732
2026-05-2453
2026-05-3151
2026-06-0756
2026-06-1462
2026-06-2141
2026-06-2834
2026-07-0537
2026-07-1227
2026-07-1940
2026-07-2646
2026-08-0234
2026-08-0938
2026-08-1633
2026-08-2343
2026-08-3048
2026-09-0632
2026-09-1352
2026-09-2053

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 week40.2-0.717.318.3 to 43.2GitHub, trailing 12 weeks2026-09-26Public query38.7
Citing works20no reading1 to 2OpenAlex, all years2026-09-26Public query2
Direct dependents3no readingno reading3 to 3Direct dependents2026-09-26Public query3
Daily dependents (unscored)5no readingno reading3 to 5deps.dev REST, unscored2026-w39Public query4
Stars11,912354no reading9,994 to 11,912GitHub stars, unscored2026-09-26Public query11,867

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

How many citations does LMCache have?

OpenAlex records 2 citing works as of 2026-09-26 (no completed yearly reading); fewer than 3 completed years, so no trend is computed.

OpenAlex citing works by completed calendar year
YearCiting works
Total indexed to date, including current year2

OpenAlex · period 2026-09-26 to 2026-09-26 · n = 0 years · method completed calendar years · updated · version 9d2fe956adbc-b1 · CSV by year

Other indexes count differently. A citation count is the number of citing works an index links to a record on a date; this page counts OpenAlex links to W4417150458 as of 2026-09-26. Check the same work: OpenAlex W4417150458 · Semantic Scholar search · Google Scholar search. Seeing a different number? Report the missing work id.

How to cite LMCache's record?

Evidaxis. LMCache measurement record. Snapshot 2026-09-26. urn:evidaxis:claim:e_V05C8HCBBV2:m3:2026-09-26. CC0-1.0. https://evidaxis.org/e/e_V05C8HCBBV2/

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

Is anyone using LMCache?

3 direct dependents on deps.dev as of not captured, under the 5-dependent floor, so no trend is computed.

Weekly dependents
PartitionDirect dependentsWeekly pointsMethod
no partition323m3 package union

Daily dependents (unscored): 5. 11,912 GitHub stars, recorded, not scored.

sparkline chart: LMCache, daily dependents, 5, 2026-w27 to 2026-w39
LMCache recorded 5 daily dependents (unscored); daily niche median not measured. deps.dev REST (unscored) · .
Captured daily series
Unscored daily dependents, as captured
PeriodDependents
2026-w273
2026-w283
2026-w293
2026-w303
2026-w313
2026-w324
2026-w334
2026-w344
2026-w354
2026-w364
2026-w374
2026-w385
2026-w395

deps.dev · period 2026-09-26 · n = 23 partitions · method m3 package union · updated · version 9d2fe956adbc-b1 · CSV

How does LMCache compare with its niche?

13 systems in Inference & Serving; niche median 32 commits per week. The reader chooses the sort order.

dot plot chart: LMCache, averaged commits per week, 40.2 vs niche median 32, 2026-09-26
LMCache at 40.2 commits a week among 13 systems; niche median 32. GitHub, current cohort · .
All 13 systems, alphabetical; choose a heading to sort
AIBrix22.2no readingno reading5,113
KTransformers4.39119,537
llama.cpp132.6no reading68129,606
llm-d32no readingno reading4,661
LMCache40.22311,912
LMDeploy13.1no readingno reading8,099
Mooncake64.31306,664
Nano-vLLM0no readingno reading15,631
Ollama23.6no reading1,078181,771
SGLang499.51021336,455
TensorRT-LLM191.2no reading014,719
vLLM536.91,58715092,723
Xinference29.2no readingno reading9,592

Evidaxis snapshot · period 2026-09-26 · n = 13 systems · method medians of measured values · updated · version 9d2fe956adbc-b1 · CSV for this niche

What changed since the last snapshot?

2 published readings changed between snapshots fcfd3a7ccdcb and 9d2fe956adbc.

slope chart: LMCache, changed published values, 2, 2026-09-19 to 2026-09-26
2 published values changed for LMCache since 2026-09-19. Evidaxis snapshots · .
Snapshot values
MetricPreviousCurrentDelta
Commits per week38.740.21.5
Citing works220
Direct dependents330
Stars11,86711,91245

Evidaxis snapshots · period 2026-09-19 to 2026-09-26 · n = 14 partitions · 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.

Paper reference on file: arXiv:2510.09665.

What is not measured for LMCache, and why

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

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: 11 weekly observations; minimum 4. Axis coverage: 1 of 3 axes measurable. Gate: not computable - 1 of 3 axes measurable

Gate: not computable - 1 of 3 axes measurable

LMCache

repo
Inference & Serving · n = 13 · LMCache/LMCache
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

· Evidaxis snapshot · 2026-09-26
Gate: not computable - 1 of 3 axes measurable
position in cohort distribution one of 13 in cohort
percentile 58 within cohort p25 p50 p75 p0 p100
percentile
p58
· 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+0.01 within cohort, log-slope +0.015/wk.0+0.01
velocity z
+0.01 σ
slope
+0.015/wk
· Evidaxis snapshot · 2026-09-26
log-slope +0.015/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
40.2
Development velocity axis: measured.
total citations
2
Citation axis: insufficient source coverage (source returned too few observations).
momentum
50.1
percentile p58
commit heatmap, last 26 weeks40.2/wk
weekly commits, 26 weeks26 weeks of commits, peak 62 in a week, 26 active weeks, 1033 total.week 1: 25 commitsweek 2: 19 commitsweek 3: 36 commitsweek 4: 47 commitsweek 5: 19 commitsweek 6: 39 commitsweek 7: 36 commitsweek 8: 32 commitsweek 9: 53 commitsweek 10: 51 commitsweek 11: 56 commitsweek 12: 62 commitsweek 13: 41 commitsweek 14: 34 commitsweek 15: 37 commitsweek 16: 27 commitsweek 17: 40 commitsweek 18: 46 commitsweek 19: 34 commitsweek 20: 38 commitsweek 21: 33 commitsweek 22: 43 commitsweek 23: 48 commitsweek 24: 32 commitsweek 25: 52 commitsweek 26: 53 commits
weeks
26
peak/wk
62
active
26
total
1033
· Evidaxis snapshot · 2026-09-26
citations by yearCitation axis: insufficient source coverage (source returned too few observations).
Daily dependents count (unscored) 5 dependents 5 direct · pypi/lmcache · deps.dev · the scored m3 axis uses weekly partitions
recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio +1.17, regime accelerating. prior slope +0.025, recent slope +0.029 per week. +0.025prior 39w+0.029recent 13w+1.17×
swing
+1.17×
regime
accelerating
windows
13w vs 39w
snapshot 1 of 1 · · m3
commit-axis Sharpe log-linear slope over residual std, value +0.062 with 95% CI +0.038 to +0.085, 50 degrees of freedom. CI excludes zero.0+0.06295% CI +0.038, +0.085+0.038+0.085
sharpe
+0.062
95% ci
+0.038, +0.085
dof
50
snapshot 1 of 1 · · m3
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 · · 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
1
shipped
3
reserved
3

shipped

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

reserved

  • code-leads-citation-lag
  • axis-alpha
  • gate-eta
snapshot 14 of 14 · · m3

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
no reading
Theil-Sen slope
no reading
Latest direct dependents
3
Confirmed-clean points
23
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

Reconstructed history

Reconstructed from git history, not a point-in-time capture. This series is separate from captured observations.

sparkline chart: LMCache, reconstructed commits, 2, 2025-w39 to 2026-w38
LMCache has 2 reconstructed commits in the latest week; reconstructed niche median not measured. Git history reconstruction · .
Reconstructed weekly commits
PeriodCommits
2025-w3922
2025-w4013
2025-w4117
2025-w4220
2025-w4319
2025-w4423
2025-w4516
2025-w4637
2025-w4729
2025-w4831
2025-w4923
2025-w5023
2025-w516
2025-w5214
2026-w0124
2026-w0220
2026-w0323
2026-w0412
2026-w0517
2026-w0618
2026-w0718
2026-w0822
2026-w0923
2026-w1034
2026-w1123
2026-w1241
2026-w1325
2026-w1419
2026-w1536
2026-w1647
2026-w1719
2026-w1839
2026-w1936
2026-w2032
2026-w2153
2026-w2251
2026-w2356
2026-w2462
2026-w2541
2026-w2634
2026-w2737
2026-w2827
2026-w2940
2026-w3046
2026-w3134
2026-w3238
2026-w3333
2026-w3443
2026-w3548
2026-w3632
2026-w3752
2026-w382
Peer signals
SystemMomentumPercentile
AIBrix58.883
KTransformers30.78
llama.cpp50.367
llm-d36.517
LMCache50.158
LMDeploy5050
Mooncake69.9100
Nano-vLLM24.50
Ollama49.542
SGLang49.133
TensorRT-LLM5675
vLLM37.725
Xinference61.592

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