import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig

model_id = "meta-llama/Llama-3.1-8B-Instruct"

from torchao.quantization import Int4WeightOnlyConfig, FqnToConfig
config = Int4WeightOnlyConfig(group_size=128)

# set default to int4 (for linears), and skip quantizing `model.layers.0.self_attn.q_proj`
quant_config = FqnToConfig({"_default": config, "model.layers.0.self_attn.q_proj": None})
quantization_config = TorchAoConfig(quant_type=quant_config)
quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", dtype=torch.bfloat16, quantization_config=quantization_config)
# lm_head is not quantized and model.layers.0.self_attn.q_proj is not quantized
print("quantized model:", quantized_model)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Manual Testing
prompt = "Hey, are you conscious? Can you talk to me?"
inputs = tokenizer(prompt, return_tensors="pt").to(quantized_model.device, quantized_model.dtype)
generated_ids = quantized_model.generate(**inputs, max_new_tokens=128)
output_text = tokenizer.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig

model_id = "facebook/opt-125m"

from torchao.quantization import Int4WeightOnlyConfig, FqnToConfig, Int8DynamicActivationInt4WeightConfig, IntxWeightOnlyConfig, PerAxis, MappingType

weight_dtype = torch.int8
granularity = PerAxis(0)
mapping_type = MappingType.ASYMMETRIC
embedding_config = IntxWeightOnlyConfig(
    weight_dtype=weight_dtype,
    granularity=granularity,
    mapping_type=mapping_type,
)
linear_config = Int8DynamicActivationInt4WeightConfig(group_size=128)
quant_config = FqnToConfig({"_default": linear_config, "model.decoder.embed_tokens": embedding_config, "model.decoder.embed_positions": None})
# set `include_embedding` to True in order to include embedding in quantization
# when `include_embedding` is True, we'll remove input embedding from `modules_not_to_convert` as well
quantization_config = TorchAoConfig(quant_type=quant_config, include_embedding=True)
quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cpu", dtype=torch.bfloat16, quantization_config=quantization_config)
print("quantized model:", quantized_model)
# make sure embedding is quantized
print("embed_tokens weight:", quantized_model.model.decoder.embed_tokens.weight)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Manual Testing
prompt = "Hey, are you conscious? Can you talk to me?"
inputs = tokenizer(prompt, return_tensors="pt").to("cpu", quantized_model.dtype)
generated_ids = quantized_model.generate(**inputs, max_new_tokens=128, cache_implementation="static")
output_text = tokenizer.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

import logging

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig

# Configure logging to see warnings and debug information
logging.basicConfig(
    level=logging.INFO, format="%(name)s - %(levelname)s - %(message)s"
)

# Enable specific loggers that might contain the serialization warnings
logging.getLogger("transformers").setLevel(logging.INFO)
logging.getLogger("torchao").setLevel(logging.INFO)
logging.getLogger("safetensors").setLevel(logging.INFO)
logging.getLogger("huggingface_hub").setLevel(logging.INFO)

model_id = "facebook/opt-125m"

from torchao.quantization import (
    Float8DynamicActivationFloat8WeightConfig,
    Int4WeightOnlyConfig,
    IntxWeightOnlyConfig,
    PerRow,
    PerAxis,
    FqnToConfig,
    Float8Tensor,
    Int4TilePackedTo4dTensor,
    IntxUnpackedToInt8Tensor,
)

float8dyn = Float8DynamicActivationFloat8WeightConfig(granularity=PerRow())
int4wo = Int4WeightOnlyConfig(int4_packing_format="tile_packed_to_4d")
intxwo = IntxWeightOnlyConfig(weight_dtype=torch.int8, granularity=PerAxis(0))

qconfig_dict = {
    # highest priority
    "model.decoder.layers.3.self_attn.q_proj": int4wo,
    "model.decoder.layers.3.self_attn.k_proj": int4wo,
    "model.decoder.layers.3.self_attn.v_proj": int4wo,
    # vllm
    "model.decoder.layers.3.self_attn.qkv_proj": int4wo,

    "re:model\.decoder\.layers\..+\.self_attn\.q_proj": float8dyn,
    "re:model\.decoder\.layers\..+\.self_attn\.k_proj": float8dyn,
    "re:model\.decoder\.layers\..+\.self_attn\.v_proj": float8dyn,
    # this should not take effect and we'll fallback to _default
    # since no full mach (missing `j` in the end)
    "re:model\.decoder\.layers\..+\.self_attn\.out_pro": float8dyn,
    # vllm
    "re:model\.decoder\.layers\..+\.self_attn\.qkv_proj": float8dyn,

    "_default": intxwo,
}
quant_config = FqnToConfig(qconfig_dict)
quantization_config = TorchAoConfig(quant_type=quant_config)
quantized_model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.bfloat16,
    quantization_config=quantization_config,
)
print("quantized model:", quantized_model)
tokenizer = AutoTokenizer.from_pretrained(model_id)
for i in range(12):
    if i == 3:
        assert isinstance(quantized_model.model.decoder.layers[i].self_attn.q_proj.weight, Int4TilePackedTo4dTensor)
        assert isinstance(quantized_model.model.decoder.layers[i].self_attn.k_proj.weight, Int4TilePackedTo4dTensor)
        assert isinstance(quantized_model.model.decoder.layers[i].self_attn.v_proj.weight, Int4TilePackedTo4dTensor)
    else:
        assert isinstance(quantized_model.model.decoder.layers[i].self_attn.q_proj.weight, Float8Tensor)
        assert isinstance(quantized_model.model.decoder.layers[i].self_attn.k_proj.weight, Float8Tensor)
        assert isinstance(quantized_model.model.decoder.layers[i].self_attn.v_proj.weight, Float8Tensor)
    assert isinstance(quantized_model.model.decoder.layers[i].self_attn.out_proj.weight, IntxUnpackedToInt8Tensor)

# Manual Testing
prompt = "What are we having for dinner?"
print("Prompt:", prompt)
inputs = tokenizer(
    prompt,
    return_tensors="pt",
).to(quantized_model.device, quantized_model.dtype)
# setting temperature to 0 to make sure result deterministic
generated_ids = quantized_model.generate(**inputs, max_new_tokens=128, temperature=0)

correct_output_text = tokenizer.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print("Response:", correct_output_text[0][len(prompt) :])


# Load model from saved checkpoint
reloaded_model = AutoModelForCausalLM.from_pretrained(
    save_to,
    device_map=torch.accelerator.current_accelerator(),
    torch_dtype=torch.bfloat16,
    # quantization_config=quantization_config,
)

generated_ids = reloaded_model.generate(**inputs, max_new_tokens=128, temperature=0)
output_text = tokenizer.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print("Response:", output_text[0][len(prompt) :])

assert(correct_output_text == output_text)

import torch
from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer
from torchao.quantization import Int8WeightOnlyConfig

quant_config = Int8WeightOnlyConfig(group_size=128)
quantization_config = TorchAoConfig(quant_type=quant_config)

# Load and quantize the model
quantized_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.1-8B-Instruct",
    dtype="auto",
    device_map="cpu",
    quantization_config=quantization_config
)
# save the quantized model
output_dir = "llama-3.1-8b-torchao-int8"
quantized_model.save_pretrained(output_dir)

# reload the quantized model
reloaded_model = AutoModelForCausalLM.from_pretrained(
    output_dir,
    device_map="auto",
    dtype=torch.bfloat16
)
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
input_text = "What are we having for dinner?"
input_ids = tokenizer(input_text, return_tensors="pt").to(reloaded_model.device.type)

output = reloaded_model.generate(**input_ids, max_new_tokens=10)
print(tokenizer.decode(output[0], skip_special_tokens=True))

import torch
from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer
from torchao.quantization import Int4WeightOnlyConfig
from torchao.quantization.quantize_.workflows import Int4PackingFormat

quant_config = Int4WeightOnlyConfig(group_size=128, int4_packing_format=Int4PackingFormat.PLAIN_INT32)
quantization_config = TorchAoConfig(quant_type=quant_config)

# Load and quantize the model
quantized_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.1-8B-Instruct",
    dtype="auto",
    device_map="cpu",
    quantization_config=quantization_config
)
# save the quantized model
output_dir = "llama-3.1-8b-torchao-int4-cpu"
quantized_model.save_pretrained(output_dir)

# reload the quantized model
reloaded_model = AutoModelForCausalLM.from_pretrained(
    output_dir,
    device_map="cpu",
    dtype=torch.bfloat16
)
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
input_text = "What are we having for dinner?"
input_ids = tokenizer(input_text, return_tensors="pt").to(reloaded_model.device.type)

output = reloaded_model.generate(**input_ids, max_new_tokens=10)
print(tokenizer.decode(output[0], skip_special_tokens=True))

from torch._inductor.utils import do_bench_using_profiling
from typing import Callable

def benchmark_fn(func: Callable, *args, **kwargs) -> float:
    """Thin wrapper around do_bench_using_profiling"""
    no_args = lambda: func(*args, **kwargs)
    time = do_bench_using_profiling(no_args)
    return time * 1e3

MAX_NEW_TOKENS = 1000
print("int4wo-128 model:", benchmark_fn(quantized_model.generate, **input_ids, max_new_tokens=MAX_NEW_TOKENS, cache_implementation="static"))

bf16_model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", dtype=torch.bfloat16)
output = bf16_model.generate(**input_ids, max_new_tokens=10, cache_implementation="static") # auto-compile
print("bf16 model:", benchmark_fn(bf16_model.generate, **input_ids, max_new_tokens=MAX_NEW_TOKENS, cache_implementation="static"))