↓ 2 callersFunctionrepeat_kv This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch, num_key_value_heads, seqlen, he
pymllm/backends/qualcomm/transformers/qwen3/modeling_qwen3.py:141
↓ 2 callersFunctionrepeat_kv This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch, num_key_value_heads, seqlen, he
pymllm/backends/qualcomm/transformers/qwen2/modeling_qwen2.py:126