GQA paged decode h32 kv16 d128 ps1
0 eligible runs
gqa-paged-attention
Batched Grouped Query Attention decode with a paged KV cache. Captured from Gemma 3 27B. GQA ratio 2:1 (32 query heads, 16 KV heads), head_dim=128, page_size=1.
Current records
No published measurement for the selected workload.
Implementations
Implementation
Runtime
Best latency
Evidence
Availability
Semantics
Inputs and outputs
qbf16 [batch_size, num_qo_heads, head_dim]
k_cachebf16 [num_pages, page_size, num_kv_heads, head_dim]
v_cachebf16 [num_pages, page_size, num_kv_heads, head_dim]
kv_indptrint32 [len_indptr]
kv_indicesint32 [num_kv_indices]
sm_scalefp32 scalar
outputbf16 [batch_size, num_qo_heads, head_dim]
lsefp32 [batch_size, num_qo_heads]
Axes and behavior
head_dimconstant = 128
num_pagesvariable
page_sizeconstant = 1
batch_sizevariable
len_indptrvariable
num_kv_headsconstant = 16
num_qo_headsconstant = 32
num_kv_indicesvariable
determinismunspecified
constraintsNo mutation or aliasing
Identity
No source imports for this operation yet.How records are decidedJSON