//clika-runtime/io.clika.runtime/Ops/scaledDotProductAttentionVarlen

scaledDotProductAttentionVarlen

[common]
fun scaledDotProductAttentionVarlen(query: Tensor, key: Tensor, value: Tensor, cuSeqlensQ: Tensor, cuSeqlensK: Tensor, maxSeqlenQ: Tensor? = null, maxSeqlenK: Tensor? = null, attnMask: Tensor? = null, isCausal: Boolean = false, qScale: Tensor? = null, kScale: Tensor? = null, vScale: Tensor? = null): Tensor

scaledDotProductAttentionVarlen(query: Tensor, key: Tensor, value: Tensor, cuSeqlensQ: Tensor, cuSeqlensK: Tensor, maxSeqlenQ: Tensor? = null, maxSeqlenK: Tensor? = null, attnMask: Tensor? = null, isCausal: Boolean = false, qScale: Tensor? = null, kScale: Tensor? = null, vScale: Tensor? = null): the scaled_dot_product_attention_varlen operator. Variable-length (packed) scaled dot-product attention: ragged batches ride one token-packed tensor plus prefix-sum offsets, no padding. Same math as scaled_dot_product_attention; the batch structure moves into cu_seqlens_*.