Method _run

tinygrad/llm/model.py:134–136

(x:Tensor, start_pos:int|UOp)

    # we pass in the weights implicitly so we unpack the GGUF on the fly
    @function(precompile=True, allow_implicit=True)
    def _run(x:Tensor, start_pos:int|UOp):
      h =     x + self._attention(self.attn_norm(x), start_pos)
      return (h + self._feed_forward(self.ffn_norm(h))).contiguous()
    return _run(x, start_pos)

class TransformerBlock(FFNBlock):