CURRENT SESSION
Run private inference
MODEL / WAITING
Waiting for live services.
RUN SUMMARY
Current live run
COVERAGE
Model cohort x actual context
No persisted run matrix available.
COMPARISON
Performance by context
No comparable persisted measurements.
ARCHIVE
Persisted runs
| Started | State | Model | Actual context | Output | TTFT | Tok/s | Total |
|---|
Loading persisted runs...
MEASUREMENTS
Selected run detail
Timing
Directional I/O
Inventory
Resources
Measured privacy invariants
Observed transport counters. Non-collusion remains protocol assumption, not measured proof.
Topology / service metricsClient, preparation, inference, process resources, and cumulative trafficCURRENT LIVE RUN
01 / CLIENTPRIVATE
Prompt, masks, sampling
WAITING0.0% CPU 0 B RAM
CPU time0.00s
Sent0 B
Received0 B
Masks0
Decode0.00 TOK/S
0 BOFFLINE SEED + ACK
02 / PREPARATIONNON-COLLUDING
Offline W*r-s inventory
WAITING0.0% CPU 0 B RAM
CPU time0.00s
Sent0 B
Received0 B
Corrections0
Online work0 GEMMs
0 BOFFLINE CORRECTIONS
03 / INFERENCEUNTRUSTED
Masked matrix execution
WAITING0.0% CPU 0 B RAM
CPU time0.00s
Sent0 B
Received0 B
Matrix runs0
First token-- TTFT
0 BONLINE TICKET + MASKED I/O
LIVE NETWORK / CAPTURED SEQUENCELatest 500 rendered; up to 65,536 operations retained in browser memoryOTEL / WAITING
CLIENTPREPARATIONINFERENCE
Run a chat to capture protocol operations.
ONLINE MASKED DATAOFFLINE PREPARATIONSIZE ON ARROW / TIME PER OP
NON-COLLUSION BOUNDARYNeither server has enough information alone. Collusion reveals activation privacy.