Search · KernelIndex

Has source0License known0Installable015 hidden

No exact results for this workload under the active filters. 200 compatible results → Best without source: 14.0 µs. Include results without source →

GQA paged decode h32 kv8 d128 ps1Operation in the gqa-paged-attention familyGQA paged prefill causal h32 kv4 d128 ps1Operation in the gqa-paged-attention familyGQA paged prefill causal h32 kv8 d128 ps1Operation in the gqa-paged-attention familyGQA paged decode h16 kv2 d128 ps1Operation in the gqa-paged-attention familyGQA paged decode h16 kv2 d128 ps64Operation in the gqa-paged-attention familyGQA paged decode h32 kv4 d128 ps64Operation in the gqa-paged-attention family

Missing a kernel here? Evidence submissions open with the contribution beta.

This search as an API call

curlkicomparison key sha256:7f4b0d2fc1ef40c2…JSON

FlashInfer-Bench · last observed 2026-03-28 · NVIDIA SOL-ExecBench · last observed 2026-08-21

Has source0License known0Installable015 hidden

No exact results for this workload under the active filters. 200 compatible results → Best without source: 14.0 µs. Include results without source →

Missing a kernel here? Evidence submissions open with the contribution beta.

This search as an API call

curlkicomparison key sha256:7f4b0d2fc1ef40c2…JSON

FlashInfer-Bench · last observed 2026-03-28 · NVIDIA SOL-ExecBench · last observed 2026-08-21

GQA paged decode h32 kv4 d128 ps1