Argus
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
dtypesfp16, fp32
Benchmark evidence
1 measurement across 1 GPU, fastest first.
Operation / workload
Hardware
Latency
Rank
Observed
Fused encoder final norm to decoder cross attention KV projectionsuite of 16 cases
NVIDIA B200
26.8µs
#8 of 11
2026-07-06
Reported · How evidence levels are derived →
Source and license
sourcenot public
revision digestsha256:1cc4737c8b747d3d742c9299d68774fb8d33f4d5a6aab7e7df3a8295c8a6c1f6
license declaredunknown
license concludedunknown
authorsArgus
imported2026-08-24
Best evidence level for this revision: reported
JSON