# coding=utf-8
# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
#
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
# and OPT implementations in this library. It has been modified from its
# original forms to accommodate minor architectural differences compared
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import Callable, List, Optional, Union

import torch
import torch.distributed as dist
from torch import nn
from transformers.activations import ACT2FN
from transformers.cache_utils import Cache, DynamicCache
from transformers.generation import GenerationMixin
from transformers.masking_utils import create_causal_mask
from transformers.modeling_layers import GradientCheckpointingLayer
from transformers.modeling_outputs import (
    BaseModelOutputWithPast,
    CausalLMOutputWithPast,
)
from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
from transformers.models.llama.configuration_llama import LlamaConfig
from transformers.models.llama.modeling_llama import (
    LlamaRMSNorm,
    LlamaRotaryEmbedding,
    apply_rotary_pos_emb,
    eager_attention_forward,
)
from transformers.processing_utils import Unpack
from transformers.utils import TransformersKwargs, logging
from transformers.utils.generic import check_model_inputs

from specforge.distributed import get_tp_group
from specforge.layers import (
    ColumnParallelLinear,
    ParallelLMHead,
    RowParallelLinear,
    VocabParallelEmbedding,
)

logger = logging.get_logger(__name__)


class TensorParallelLlamaMLP(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
        self.hidden_size = config.hidden_size
        self.intermediate_size = config.intermediate_size

        # self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=config.mlp_bias)
        # self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=config.mlp_bias)
        # self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=config.mlp_bias)

        self.tp_group = get_tp_group()
        self.gate_proj = ColumnParallelLinear(
            self.hidden_size, self.intermediate_size, bias=config.mlp_bias
        )
        self.up_proj = ColumnParallelLinear(
            self.hidden_size, self.intermediate_size, bias=config.mlp_bias
        )
        self.down_proj = RowParallelLinear(
            self.intermediate_size, self.hidden_size, bias=config.mlp_bias
        )
        self.act_fn = ACT2FN[config.hidden_act]

    def forward(self, x):
        down_proj = self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))
        dist.all_reduce(down_proj, op=dist.ReduceOp.SUM, group=self.tp_group)
        return down_proj


class TensorParallelLlamaAttention(nn.Module):
    """Multi-headed attention from 'Attention Is All You Need' paper"""

    def __init__(self, config: LlamaConfig, layer_idx: int):
        super().__init__()
        self.config = config
        self.layer_idx = layer_idx
        self.head_dim = getattr(
            config, "head_dim", config.hidden_size // config.num_attention_heads
        )
        self.num_key_value_groups = (
            config.num_attention_heads // config.num_key_value_heads
        )
        self.scaling = self.head_dim**-0.5
        self.attention_dropout = config.attention_dropout
        self.is_causal = True

        # self.q_proj = nn.Linear(
        #     config.hidden_size, config.num_attention_heads * self.head_dim, bias=config.attention_bias
        # )
        # self.k_proj = nn.Linear(
        #     config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.attention_bias
        # )
        # self.v_proj = nn.Linear(
        #     config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.attention_bias
        # )
        # self.o_proj = nn.Linear(
        #     config.num_attention_heads * self.head_dim, config.hidden_size, bias=config.attention_bias
        # )

        # distributed linear layers
        self.tp_group = get_tp_group()
        self.q_proj = ColumnParallelLinear(
            config.hidden_size,
            config.num_attention_heads * self.head_dim,
            bias=config.attention_bias,
        )
        self.k_proj = ColumnParallelLinear(
            config.hidden_size,
            config.num_key_value_heads * self.head_dim,
            bias=config.attention_bias,
        )
        self.v_proj = ColumnParallelLinear(
            config.hidden_size,
            config.num_key_value_heads * self.head_dim,
            bias=config.attention_bias,
        )
        self.o_proj = RowParallelLinear(
            config.num_attention_heads * self.head_dim,
            config.hidden_size,
            bias=config.attention_bias,
        )

    def forward(
        self,
        hidden_states: torch.Tensor,
        position_embeddings: tuple[torch.Tensor, torch.Tensor],
        attention_mask: Optional[torch.Tensor],
        past_key_values: Optional[Cache] = None,
        cache_position: Optional[torch.LongTensor] = None,
        **kwargs: Unpack[TransformersKwargs],
    ) -> tuple[torch.Tensor, torch.Tensor]:
        input_shape = hidden_states.shape[:-1]
        hidden_shape = (*input_shape, -1, self.head_dim)

        query_states = self.q_proj(hidden_states).view(hidden_shape).transpose(1, 2)
        key_states = self.k_proj(hidden_states).view(hidden_shape).transpose(1, 2)
        value_states = self.v_proj(hidden_states).view(hidden_shape).transpose(1, 2)

        cos, sin = position_embeddings
        query_states, key_states = apply_rotary_pos_emb(
            query_states, key_states, cos, sin
        )

        if past_key_values is not None:
            # sin and cos are specific to RoPE models; cache_position needed for the static cache
            cache_kwargs = {"sin": sin, "cos": cos, "cache_position": cache_position}
            key_states, value_states = past_key_values.update(
                key_states, value_states, self.layer_idx, cache_kwargs
            )

        attention_interface: Callable = eager_attention_forward
        if self.config._attn_implementation != "eager":
            attention_interface = ALL_ATTENTION_FUNCTIONS[
                self.config._attn_implementation
            ]

        attn_output, attn_weights = attention_interface(
            self,
            query_states,
            key_states,
            value_states,
            attention_mask,
            dropout=0.0 if not self.training else self.attention_dropout,
            scaling=self.scaling,
            **kwargs,
        )

        attn_output = attn_output.reshape(*input_shape, -1).contiguous()
        attn_output = self.o_proj(attn_output)
        dist.all_reduce(attn_output, op=dist.ReduceOp.SUM, group=self.tp_group)
        return attn_output, attn_weights


class TensorParallelLlamaDecoderLayer(GradientCheckpointingLayer):
    def __init__(self, config: LlamaConfig, layer_idx: int):
        super().__init__()
        self.hidden_size = config.hidden_size

        self.self_attn = TensorParallelLlamaAttention(
            config=config, layer_idx=layer_idx
        )

        self.mlp = TensorParallelLlamaMLP(config)
        self.input_layernorm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
        self.post_attention_layernorm = LlamaRMSNorm(
            config.hidden_size, eps=config.rms_norm_eps
        )

    def forward(
        self,
        hidden_states: torch.Tensor,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[Cache] = None,
        use_cache: Optional[bool] = False,
        cache_position: Optional[torch.LongTensor] = None,
        position_embeddings: Optional[
            tuple[torch.Tensor, torch.Tensor]
        ] = None,  # necessary, but kept here for BC
        **kwargs: Unpack[TransformersKwargs],
    ) -> torch.Tensor:
        residual = hidden_states
        hidden_states = self.input_layernorm(hidden_states)
        # Self Attention
        hidden_states, _ = self.self_attn(
            hidden_states=hidden_states,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_values=past_key_values,
            use_cache=use_cache,
            cache_position=cache_position,
            position_embeddings=position_embeddings,
            **kwargs,
        )
        hidden_states = residual + hidden_states

        # Fully Connected
        residual = hidden_states
        hidden_states = self.post_attention_layernorm(hidden_states)
        hidden_states = self.mlp(hidden_states)
        hidden_states = residual + hidden_states
        return hidden_states


class LlamaPreTrainedModel(PreTrainedModel):
    config: LlamaConfig
    base_model_prefix = "model"
    supports_gradient_checkpointing = True
    _no_split_modules = ["TensorParallelLlamaDecoderLayer"]
    _skip_keys_device_placement = ["past_key_values"]
    _supports_flash_attn = True
    _supports_sdpa = True
    _supports_flex_attn = True

    _can_compile_fullgraph = True
    _supports_attention_backend = True
    _can_record_outputs = {}


class LlamaModel(LlamaPreTrainedModel):
    def __init__(self, config: LlamaConfig):
        super().__init__(config)
        self.padding_idx = config.pad_token_id
        self.vocab_size = config.vocab_size

        self.embed_tokens = VocabParallelEmbedding(
            config.vocab_size, config.hidden_size, self.padding_idx
        )
        self.layers = nn.ModuleList(
            [
                TensorParallelLlamaDecoderLayer(config, layer_idx)
                for layer_idx in range(config.num_hidden_layers)
            ]
        )
        self.norm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
        self.rotary_emb = LlamaRotaryEmbedding(config=config)
        self.gradient_checkpointing = False

        # Initialize weights and apply final processing
        self.post_init()

    @check_model_inputs
    def forward(
        self,
        input_ids: Optional[torch.LongTensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[Cache] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        cache_position: Optional[torch.LongTensor] = None,
        use_cache: Optional[bool] = None,
        **kwargs: Unpack[TransformersKwargs],
    ) -> BaseModelOutputWithPast:
        if (input_ids is None) ^ (inputs_embeds is not None):
            raise ValueError(
                "You must specify exactly one of input_ids or inputs_embeds"
            )

        layers_to_output_hidden_states: Optional[List[int]] = kwargs.pop(
            "layers_to_output_hidden_states", None
        )

        if inputs_embeds is None:
            inputs_embeds: torch.Tensor = self.embed_tokens(input_ids)

        if use_cache and past_key_values is None:
            past_key_values = DynamicCache(config=self.config)

        if cache_position is None:
            past_seen_tokens = (
                past_key_values.get_seq_length() if past_key_values is not None else 0
            )
            cache_position: torch.Tensor = torch.arange(
                past_seen_tokens,
                past_seen_tokens + inputs_embeds.shape[1],
                device=inputs_embeds.device,
            )

        if position_ids is None:
            position_ids = cache_position.unsqueeze(0)

        causal_mask = create_causal_mask(
            config=self.config,
            input_embeds=inputs_embeds,
            attention_mask=attention_mask,
            cache_position=cache_position,
            past_key_values=past_key_values,
            position_ids=position_ids,
        )

        hidden_states = inputs_embeds
        position_embeddings = self.rotary_emb(hidden_states, position_ids)

        all_hidden_states = ()
        for idx, decoder_layer in enumerate(self.layers):
            hidden_states = decoder_layer(
                hidden_states,
                attention_mask=causal_mask,
                position_ids=position_ids,
                past_key_values=past_key_values,
                cache_position=cache_position,
                position_embeddings=position_embeddings,
                **kwargs,
            )
            if (
                layers_to_output_hidden_states is None
                or idx in layers_to_output_hidden_states
            ):
                all_hidden_states += (hidden_states,)

        hidden_states = self.norm(hidden_states)
        return BaseModelOutputWithPast(
            last_hidden_state=hidden_states,
            past_key_values=past_key_values,
            hidden_states=all_hidden_states,
        )


class LlamaForCausalLM(LlamaPreTrainedModel, GenerationMixin):
    _tied_weights_keys = ["lm_head.weight"]
    _tp_plan = {"lm_head": "colwise_rep"}
    _pp_plan = {"lm_head": (["hidden_states"], ["logits"])}

    def __init__(self, config):
        super().__init__(config)
        self.model = LlamaModel(config)
        self.vocab_size = config.vocab_size

        # distributed the lm head
        self.lm_head = ParallelLMHead(config.hidden_size, config.vocab_size, bias=False)

        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.model.embed_tokens

    def set_input_embeddings(self, value):
        self.model.embed_tokens = value

    def get_output_embeddings(self):
        return self.lm_head

    def set_output_embeddings(self, new_embeddings):
        self.lm_head = new_embeddings

    def set_decoder(self, decoder):
        self.model = decoder

    def get_decoder(self):
        return self.model

    def forward(
        self,
        input_ids: Optional[torch.LongTensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[Cache] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        labels: Optional[torch.LongTensor] = None,
        use_cache: Optional[bool] = None,
        cache_position: Optional[torch.LongTensor] = None,
        logits_to_keep: Union[int, torch.Tensor] = 0,
        **kwargs: Unpack[TransformersKwargs],
    ) -> CausalLMOutputWithPast:
        r"""
        Example:

        ```python
        >>> from transformers import AutoTokenizer, LlamaForCausalLM

        >>> model = LlamaForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")

        >>> prompt = "Hey, are you conscious? Can you talk to me?"
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```"""

        outputs: BaseModelOutputWithPast = self.model(
            input_ids=input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_values=past_key_values,
            inputs_embeds=inputs_embeds,
            use_cache=use_cache,
            cache_position=cache_position,
            **kwargs,
        )

        hidden_states = outputs.last_hidden_state
        # Only compute necessary logits, and do not upcast them to float if we are not computing the loss
        slice_indices = (
            slice(-logits_to_keep, None)
            if isinstance(logits_to_keep, int)
            else logits_to_keep
        )
        logits = self.lm_head(hidden_states[:, slice_indices, :], gather_output=True)

        loss = None
        if labels is not None:
            loss = self.loss_function(
                logits=logits,
                labels=labels,
                vocab_size=self.config.vocab_size,
                **kwargs,
            )

        return CausalLMOutputWithPast(
            loss=loss,
            logits=logits,
            past_key_values=outputs.past_key_values,
            hidden_states=outputs.hidden_states,
        )


__all__ = [
    "LlamaForCausalLM",
    "LlamaModel",
]