llama-3-1-70b
best known per operation on the selected GPU
11 operations · 3 families · 20 eligible runs
0 of 11 operations have a usable best known on NVIDIA B200 · 11 without one
Best known on NVIDIA B200
Operation · workload
Best known
Record
Trust
Observed
gqa-paged-attention1 operation
GQA paged prefill causal h16 kv2 d128 ps64bf16 · [1, 16, 128]flashinfer / wrapper69a524not usable16.8µsReported · Apache-2.0 · source2026-04-09
No entry in this cohort passes the usability policy (no install recipe); the fastest known is shown. Measured by the source's own harness. Ranked by its metric under ranking-v1.
source mirroredApache-2.0no install recipeCohort on the operation page →View source →Vendor the source →Run detail →
Coverage gaps on NVIDIA B200
Operation
Family
Status
gqa-paged-attention
measured · no usable entry (no install recipe)
No eligible evidence yet for these operations. Challenges →
Sources: FlashInfer-Bench (2026-04-09) · Apache-2.0How comparison worksJSON