Compare runs
cohort sha256:50b4ca648f11e029… · source-native profile
ranking-v1
no ranks: not comparable
Comparison identity
operation
moe-fp8-block-scale-ds-routing-topk8-ng8-kg4-e32-h7168-i2048
workload
seq_len = 7 · bf16/fp32/fp8_e4m3 · cbd281ee
protocol
flashinfer-bench · 7d44d206
environment
NVIDIA B200 · f4292a8b
correctness policy
64fb869e
metric
latency mean (ns)
Context · 10 fields›
architecture
unknown
CUDA
12.8
driver
unknown
framework
pytorch 2.8.0+cu128
samples
unknown
evidence
reproducible
license
Apache-2.0
source
available
status
passed
observed
2025-10-16
No winner: these runs didn't measure the same thing. The rows above show what differs. Why comparable?
Add run ›
Export ›
Markdown CSV JSON
gpt-5-2025-08-07_cuda_a2d8ca · sha256:bed65b694af90… · observed 2025-10-16