phi-4-14b
best known per operation on the selected GPU
1 operation · 1 family · 20 eligible runs
0 of 1 operations have a usable best known on NVIDIA B200 · 1 without one
Best known on NVIDIA B200
Operation · workload
Best known
Record
Trust
Observed
gqa-paged-attention1 operation
GQA paged prefill causal h40 kv10 d128 ps1bf16 · [1, 40, 128]flashinfer / wrapper5222a7not usable16.7µsReproduction-ready · Apache-2.0 · source2026-04-07
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 (2026-04-07) · Apache-2.0How comparison worksJSON