# Install AutoGPTQ
pip install auto-gptq

# With Triton (Linux only, faster)
pip install auto-gptq[triton]

# With CUDA extensions (faster)
pip install auto-gptq --no-build-isolation

# Full installation
pip install auto-gptq transformers accelerate

from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM

# Load quantized model from HuggingFace
model_name = "TheBloke/Llama-2-7B-Chat-GPTQ"

model = AutoGPTQForCausalLM.from_quantized(
    model_name,
    device="cuda:0",
    use_triton=False  # Set True on Linux for speed
)

tokenizer = AutoTokenizer.from_pretrained(model_name)

# Generate
prompt = "Explain quantum computing"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0]))

from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
from datasets import load_dataset

# Load model
model_name = "meta-llama/Llama-2-7b-chat-hf"
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Quantization config
quantize_config = BaseQuantizeConfig(
    bits=4,              # 4-bit quantization
    group_size=128,      # Group size (recommended: 128)
    desc_act=False,      # Activation order (False for CUDA kernel)
    damp_percent=0.01    # Dampening factor
)

# Load model for quantization
model = AutoGPTQForCausalLM.from_pretrained(
    model_name,
    quantize_config=quantize_config
)

# Prepare calibration data
dataset = load_dataset("c4", split="train", streaming=True)
calibration_data = [
    tokenizer(example["text"])["input_ids"][:512]
    for example in dataset.take(128)
]

# Quantize
model.quantize(calibration_data)

# Save quantized model
model.save_quantized("llama-2-7b-gptq")
tokenizer.save_pretrained("llama-2-7b-gptq")

# Push to HuggingFace
model.push_to_hub("username/llama-2-7b-gptq")

Weight matrix: [1024, 4096] = 4.2M elements

Group size = 128:
- Groups: 4.2M / 128 = 32,768 groups
- Each group: own 4-bit scale + zero-point
- Result: Better granularity → better accuracy

from auto_gptq import BaseQuantizeConfig

config = BaseQuantizeConfig(
    bits=4,              # 4-bit quantization
    group_size=128,      # Standard group size
    desc_act=False,      # Faster CUDA kernel
    damp_percent=0.01    # Dampening factor
)

config = BaseQuantizeConfig(
    bits=3,              # 3-bit (more compression)
    group_size=128,      # Keep standard group size
    desc_act=True,       # Better accuracy (slower)
    damp_percent=0.01
)

config = BaseQuantizeConfig(
    bits=4,
    group_size=32,       # Smaller groups (better accuracy)
    desc_act=True,       # Activation reordering
    damp_percent=0.005   # Lower dampening
)

model = AutoGPTQForCausalLM.from_quantized(
    model_name,
    device="cuda:0",
    use_exllama=True,      # Use ExLlamaV2
    exllama_config={"version": 2}
)

# Quantize with Marlin format
config = BaseQuantizeConfig(
    bits=4,
    group_size=128,
    desc_act=False  # Required for Marlin
)

model.quantize(calibration_data, use_marlin=True)

# Load with Marlin
model = AutoGPTQForCausalLM.from_quantized(
    model_name,
    device="cuda:0",
    use_marlin=True  # 2× faster on A100/H100
)

model = AutoGPTQForCausalLM.from_quantized(
    model_name,
    device="cuda:0",
    use_triton=True  # Linux only
)

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load quantized model (transformers auto-detects GPTQ)
model = AutoModelForCausalLM.from_pretrained(
    "TheBloke/Llama-2-13B-Chat-GPTQ",
    device_map="auto",
    trust_remote_code=False
)

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Llama-2-13B-Chat-GPTQ")

# Use like any transformers model
inputs = tokenizer("Hello", return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=100)

from transformers import AutoModelForCausalLM
from peft import prepare_model_for_kbit_training, LoraConfig, get_peft_model

# Load GPTQ model
model = AutoModelForCausalLM.from_pretrained(
    "TheBloke/Llama-2-7B-GPTQ",
    device_map="auto"
)

# Prepare for LoRA training
model = prepare_model_for_kbit_training(model)

# LoRA config
lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    target_modules=["q_proj", "v_proj"],
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM"
)

# Add LoRA adapters
model = get_peft_model(model, lora_config)

# Fine-tune (memory efficient!)
# 70B model trainable on single A100 80GB

# Automatic device mapping
model = AutoGPTQForCausalLM.from_quantized(
    "TheBloke/Llama-2-70B-GPTQ",
    device_map="auto",  # Automatically split across GPUs
    max_memory={0: "40GB", 1: "40GB"}  # Limit per GPU
)

# Manual device mapping
device_map = {
    "model.embed_tokens": 0,
    "model.layers.0-39": 0,  # First 40 layers on GPU 0
    "model.layers.40-79": 1,  # Last 40 layers on GPU 1
    "model.norm": 1,
    "lm_head": 1
}

model = AutoGPTQForCausalLM.from_quantized(
    model_name,
    device_map=device_map
)

# Offload some layers to CPU (for very large models)
model = AutoGPTQForCausalLM.from_quantized(
    "TheBloke/Llama-2-405B-GPTQ",
    device_map="auto",
    max_memory={
        0: "80GB",  # GPU 0
        1: "80GB",  # GPU 1
        2: "80GB",  # GPU 2
        "cpu": "200GB"  # Offload overflow to CPU
    }
)

# Process multiple prompts efficiently
prompts = [
    "Explain AI",
    "Explain ML",
    "Explain DL"
]

inputs = tokenizer(prompts, return_tensors="pt", padding=True).to("cuda")

outputs = model.generate(
    **inputs,
    max_new_tokens=100,
    pad_token_id=tokenizer.eos_token_id
)

for i, output in enumerate(outputs):
    print(f"Prompt {i}: {tokenizer.decode(output)}")

# Find GPTQ models on HuggingFace
https://huggingface.co/models?library=gptq

from auto_gptq import AutoGPTQForCausalLM

# Automatically downloads from HuggingFace
model = AutoGPTQForCausalLM.from_quantized(
    "TheBloke/Llama-2-70B-Chat-GPTQ",
    device="cuda:0"
)