Amir M. Mir | SF Tensor
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
dtypesfp32
Benchmark evidence
1 measurement across 1 GPU, fastest first.
Operation / workload
Hardware
Latency
Rank
Observed
Cross attention QKV projection with GQA repeat backwardsuite of 16 cases
NVIDIA B200
183.1µs
#10 of 16
2026-07-11
Reported · How evidence levels are derived →
Source and license
sourcenot public
revision digestsha256:b9e88551a287690c393b652030651aa74fe8ef6c382e2a51e1ffeae206d679e9
license declaredunknown
license concludedunknown
authorsAmir M. Mir | SF Tensor
imported2026-08-24
Best evidence level for this revision: reported
JSON