gundam00
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, int64
Benchmark evidence
1 measurement across 1 GPU, fastest first.
Operation / workload
Hardware
Latency
Rank
Observed
Grouped query attention with YaRN RoPE and QK normsuite of 16 cases
NVIDIA B200
667.2µs
#9 of 11
2026-04-21
Reported · How evidence levels are derived →
Source and license
sourcenot public
revision digestsha256:bbb51ce40560fe14af6be00b7fbbe4a10fe32851614c4c883d75e03bf339b85c
license declaredunknown
license concludedunknown
authorsgundam00
imported2026-08-24
Best evidence level for this revision: reported
JSON