Databricks
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
Fused attention QK matmul scale mask softmax backwardsuite of 16 cases
NVIDIA B200
149.8µs
#3 of 12
2026-07-01
Reported · How evidence levels are derived →
Source and license
sourcenot public
revision digestsha256:1f9470ab2eb4a5596d31b24ad036605a88275237cb79863782fec4ad41b43b37
license declaredunknown
license concludedunknown
authorsDatabricks
imported2026-08-24
Best evidence level for this revision: reported
JSON