repeat_kv: return

Read the equation

In repeat_kv, this statement returns the displayed result. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.

Terms & definitions

The recovered passage does not supply a separate symbol table. Read the source context for the notation used in this version; familiar letters may carry different meanings in other builds.

How it works

1. Read the displayed expression together with the surrounding source statement; it is retained as an expression rather than silently completed into an equality.

2. Substitute the source-defined variables or recorded values and follow the displayed arithmetic and indexing exactly.

3. Use this version’s variable definitions and update order. The same symbol may be assigned a different meaning in another build.

Assumptions & limits

Source recovery establishes that the expression appears in this record. Its mathematical validity, implementation behavior, and interpretation must be assessed separately. See the linked source and research notes for the checks available for this version.

Original context

None, :, :].expand(batch,
                                                     num_key_value_heads,
                                                     n_rep, slen, head_dim)
    return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen,
                                 head_dim)


# Copied from transformers.models.llama.modeling_llama.LlamaAttention with Llama->DeepseekV3

return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen,
                                 head_dim)

Related builds