Compare runs
cohort sha256:717c794ad58d64bd… · source-native profile
ranking-v1
no ranks: not comparable
Comparison identity
operation
gqa-ragged-prefill-causal-h32-kv8-d64
workload
total_q = 35 · total_kv = 35 · len_indptr = 2 · bf16 · 3c23d1a5
protocol
flashinfer-bench · 7d44d206
environment
NVIDIA B200 · 83c9b6e7
correctness policy
64fb869e
metric
latency mean (ns)
Context · 10 fields›
architecture
sm_100
CUDA
13.0
driver
unknown
framework
pytorch 2.11.0+cu130
samples
unknown
evidence
reported
license
Apache-2.0
source
available
status
passed
observed
2026-04-20
No winner: these runs didn't measure the same thing. The rows above show what differs. Why comparable?
Add run ›
Export ›
Markdown CSV JSON
flashinfer_wrapper_44b034 · sha256:9d6c64e135905… · observed 2026-04-20