Benchmarks¶

Nightly snapshot

GPU NVIDIA H200 · commit b473facc3f51 · run date 2026-08-24 · 191 ops, 1137 workloads · nightly run

Page rendered 2026-08-24 22:31 UTC from the nightly-bench snapshot.

Environment¶


image	`ghcr.io/tile-ai/tileops-runner:cu132-torch2.13-tl-afcebed1-1`
gpu	`NVIDIA H200`
driver	`595.71.05`
cuda	`13.2`
torch	`2.13.0+cu132`
tilelang	`0.1.11+cu132.gitafcebed1`
timer	`cupti`

One process, common inputs. Every implementation of an op is timed on the same tensors in the same process, in forward and then reversed order so drift does not land on whichever ran last.
A fixed warmup and measurement budget per implementation, reported as the median over however many samples fit in it, with L2 cleared between iterations.
Compilation and workspace setup excluded.
Device time is what is compared — the union of the intervals the device spent executing the call's kernels, collected through CUPTI. A run that cannot collect device activity fails rather than falling back to a different clock.

191 of 191 ops are measured against a real alternative — a tuned library kernel or a native PyTorch op — on the identical workload. The rest run against an eager reference only, which is not a bar worth reporting a win against.
Absent from every table: 0 workloads errored and 13 were skipped in this run.