Compare runs
cohort sha256:573e2e3c4570953e… · source-native profile
ranking-v1
no ranks: not comparable
Comparison identity
operation
gqa-paged-decode-h32-kv8-d64-ps64
workload
num_pages = 79 · batch_size = 1 · len_indptr = 2 · num_kv_indices = 15 · bf16 · 0fa58ff1
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_68ff49 · sha256:61ab274f4bcb2… · observed 2026-04-20