fastchat/model/monkey_patch_non_inplace.py [40:72]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    bsz, q_len, _ = hidden_states.size()

    query_states = (
        self.q_proj(hidden_states)
        .view(bsz, q_len, self.num_heads, self.head_dim)
        .transpose(1, 2)
    )
    key_states = (
        self.k_proj(hidden_states)
        .view(bsz, q_len, self.num_heads, self.head_dim)
        .transpose(1, 2)
    )
    value_states = (
        self.v_proj(hidden_states)
        .view(bsz, q_len, self.num_heads, self.head_dim)
        .transpose(1, 2)
    )

    kv_seq_len = key_states.shape[-2]
    if past_key_value is not None:
        kv_seq_len += past_key_value[0].shape[-2]
    cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
    query_states, key_states = apply_rotary_pos_emb(
        query_states, key_states, cos, sin, position_ids
    )
    # [bsz, nh, t, hd]

    if past_key_value is not None:
        # reuse k, v, self_attention
        key_states = torch.cat([past_key_value[0], key_states], dim=2)
        value_states = torch.cat([past_key_value[1], value_states], dim=2)

    past_key_value = (key_states, value_states) if use_cache else None
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



fastchat/train/llama_flash_attn_monkey_patch.py [27:58]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    bsz, q_len, _ = hidden_states.size()

    query_states = (
        self.q_proj(hidden_states)
        .view(bsz, q_len, self.num_heads, self.head_dim)
        .transpose(1, 2)
    )
    key_states = (
        self.k_proj(hidden_states)
        .view(bsz, q_len, self.num_heads, self.head_dim)
        .transpose(1, 2)
    )
    value_states = (
        self.v_proj(hidden_states)
        .view(bsz, q_len, self.num_heads, self.head_dim)
        .transpose(1, 2)
    )  # shape: (b, num_heads, s, head_dim)

    kv_seq_len = key_states.shape[-2]
    if past_key_value is not None:
        kv_seq_len += past_key_value[0].shape[-2]
    cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
    query_states, key_states = apply_rotary_pos_emb(
        query_states, key_states, cos, sin, position_ids
    )

    if past_key_value is not None:
        # reuse k, v
        key_states = torch.cat([past_key_value[0], key_states], dim=2)
        value_states = torch.cat([past_key_value[1], value_states], dim=2)

    past_key_value = (key_states, value_states) if use_cache else None
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -