For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Mojo function
q_gmem_shape_fused
def q_gmem_shape_fused[*, group: Int, q_num_heads: Int, depth: Int]() -> Coord[ComptimeInt[Int(-1)], ComptimeInt[(q_num_heads // group)], ComptimeInt[group], ComptimeInt[depth]]
Computes the rank-4 global-memory shape for a decoding or fused-GQA Q tensor TMA tile.
Parameters:
- โgroup (
Int): Grouped-query attention group size, in query heads per KV head. - โq_num_heads (
Int): Number of query attention heads. - โdepth (
Int): Head dimension of the attention layer, in elements.
Returns: