doubleAI
License unknown
Use it
Benchmark submission only · no public source · license unknown
No install recipe recorded for this revision.
interfaceunknown
Compatibility
measured onNVIDIA B200
declared hardwareNVIDIA B200
architecturessm_100
dtypesbf16, fp32
Benchmark evidence
1 measurement across 1 GPU, fastest first.
Operation / workload
Hardware
Latency
Rank
Observed
Attention QKV with QK norm single kernel backwardsuite of 16 cases
NVIDIA B200
28.0µs
#2 of 13
2026-06-26
Reported · How evidence levels are derived →
Source and license
sourcenot public
revision digestsha256:538623a2f1defb32bdd3e65a9f5736c204bd90912e20431c3b7aee57121e5085
license declaredunknown
license concludedunknown
authorsdoubleAI
imported2026-08-24
Best evidence level for this revision: reported
JSON