LongCat-Flash-Thinking-ZigZag

from flash_mla_interface import flash_mla_varlen_func, flash_mla_with_kvcache
from streaming_sparse_attn_interface import streaming_sparse_attn_varlen_func, streaming_sparse_attn_with_kvcache


full_attn_out = flash_mla_varlen_func_(
    q, # [nnz_q, num_heads_q, head_dim_qk]
    k, # [nnz_k, num_heads_k, head_dim_qk]
    v, # [nnz_k, num_heads_v, head_dim_vo]
    cu_seqlens_q,
    cu_seqlens_k,
    max_seqlen_q,
    max_seqlen_k,
    softmax_scale,
    causal=True
)
stream_attn_out = streaming_sparse_attn_varlen_func_(
    q,
    k,
    v,
    cu_seqlens_q,
    cu_seqlens_k,
    max_seqlen_q,
    max_seqlen_k,
    softmax_scale,
    causal=True
)
        

full_attn_out = flash_mla_with_kvcache(
    q, # [batch_size, seqlen_q, num_heads_q, head_dim_nope + head_dim_rope]
    blocked_k, # [num_pages, page_size, num_heads_k, head_dim_nope + head_dim_rope]
    cache_seqlens,
    block_table,
    head_dim_nope, 
    softmax_scale,
    causal=True
)
stream_attn_out = streaming_sparse_attn_with_kvcache(
    q,
    blocked_k,
    cache_seqlens,
    block_table,
    head_dim_nope,
    softmax_scale,
    causal=True
)