a ½ Àh˜ ã @sxddlZddlmZddlmZzeƒr4ddlmZWneyHYn0d ejj ej ej ej ej eej dœdd„Z dS) éNé)ÚPagedAttentionCache)Úis_flash_attn_2_available)Úflash_attn_varlen_func)ÚmoduleÚqÚkÚvÚattention_maskÚcacheÚreturnc Ksè|j|||jfi| ¤Ž\}}t|ddƒs,dn|jdf} | durD| j}d| vrZd|  d¡ini}|| dd¡ d¡ ¡| dd¡ d¡ ¡| dd¡ d¡ ¡|  t j ¡|  t j ¡  ¡|| f|j d | d œ|¤Ž}t|tƒrà|d}|dfS) aæPerform the forward pass of attention with paged key-value cache. This function handles the cache updates and performs the attention computation using the flash_attn_varlen_func for efficient processing. Args: q: (total_q, nheads, headdim), where total_q = total number of query tokens in the batch. k: (total_k, nheads_k, headdim), where total_k = total number of key tokens in the batch. but if there is a block table it can be the full k v: (total_k, nheads_k, headdim), where total_k = total number of key tokens in the batch. but if there is a block table it can be the full v cu_seq_lens_q: (batch_size + 1,), dtype torch.int32. The cumulative sequence lengths of the sequences in the batch, used to index into q. cu_seq_lens_k: (batch_size + 1,), dtype torch.int32. The cumulative sequence lengths of the sequences in the batch, used to index into kv. max_seqlen_q: int. Maximum query sequence length in the batch. max_seqlen_k: int. Maximum key sequence length in the batch. dropout_p: float. Dropout probability. softmax_scale: float. The scaling of QK^T before applying softmax. Default to 1 / sqrt(headdim). causal: bool. Whether to apply causal attention mask (e.g., for auto-regressive modeling). window_size: (left, right). If not (-1, -1), implements sliding window local attention. softcap: float. Anything > 0 activates softcapping attention. Úsliding_windowF)éÿÿÿÿrrNZs_auxérT)Z softmax_scaleZcausalZ window_size)ÚupdateZ layer_idxÚgetattrr rÚgetZ transposeZsqueezeÚ contiguousÚtoÚtorchZint32ÚcloneZscalingÚ isinstanceÚtuple)rrrr r r Z cu_seq_lens_qZ cu_seq_lens_kZ max_seqlen_qZ max_seqlen_kZ block_tablesÚimplementationÚkwargsr rZ custom_kwargsZ attn_output©rúa/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/integrations/flash_paged.pyÚpaged_attention_forwards.% ùö ô r)NNNNNNNN) rZgeneration.continuous_batchingrÚutilsrZ flash_attnrÚ ExceptionÚnnÚModuleZTensorrrrrrÚs0   ôò