# Clone llama.cpp
git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp

# Build (CPU)
make

# Build with CUDA (NVIDIA)
make GGML_CUDA=1

# Build with Metal (Apple Silicon)
make GGML_METAL=1

# Install Python bindings (optional)
pip install llama-cpp-python

# Install requirements
pip install -r requirements.txt

# Convert HuggingFace model to GGUF (FP16)
python convert_hf_to_gguf.py ./path/to/model --outfile model-f16.gguf

# Or specify output type
python convert_hf_to_gguf.py ./path/to/model \
    --outfile model-f16.gguf \
    --outtype f16

# Basic quantization to Q4_K_M
./llama-quantize model-f16.gguf model-q4_k_m.gguf Q4_K_M

# Quantize with importance matrix (better quality)
./llama-imatrix -m model-f16.gguf -f calibration.txt -o model.imatrix
./llama-quantize --imatrix model.imatrix model-f16.gguf model-q4_k_m.gguf Q4_K_M

# CLI inference
./llama-cli -m model-q4_k_m.gguf -p "Hello, how are you?"

# Interactive mode
./llama-cli -m model-q4_k_m.gguf --interactive

# With GPU offload
./llama-cli -m model-q4_k_m.gguf -ngl 35 -p "Hello!"

# 1. Download model
huggingface-cli download meta-llama/Llama-3.1-8B --local-dir ./llama-3.1-8b

# 2. Convert to GGUF (FP16)
python convert_hf_to_gguf.py ./llama-3.1-8b \
    --outfile llama-3.1-8b-f16.gguf \
    --outtype f16

# 3. Quantize
./llama-quantize llama-3.1-8b-f16.gguf llama-3.1-8b-q4_k_m.gguf Q4_K_M

# 4. Test
./llama-cli -m llama-3.1-8b-q4_k_m.gguf -p "Hello!" -n 50

# 1. Convert to GGUF
python convert_hf_to_gguf.py ./model --outfile model-f16.gguf

# 2. Create calibration text (diverse samples)
cat > calibration.txt << 'EOF'
The quick brown fox jumps over the lazy dog.
Machine learning is a subset of artificial intelligence.
Python is a popular programming language.
# Add more diverse text samples...
EOF

# 3. Generate importance matrix
./llama-imatrix -m model-f16.gguf \
    -f calibration.txt \
    --chunk 512 \
    -o model.imatrix \
    -ngl 35  # GPU layers if available

# 4. Quantize with imatrix
./llama-quantize --imatrix model.imatrix \
    model-f16.gguf \
    model-q4_k_m.gguf \
    Q4_K_M

#!/bin/bash
MODEL="llama-3.1-8b-f16.gguf"
IMATRIX="llama-3.1-8b.imatrix"

# Generate imatrix once
./llama-imatrix -m $MODEL -f wiki.txt -o $IMATRIX -ngl 35

# Create multiple quantizations
for QUANT in Q4_K_M Q5_K_M Q6_K Q8_0; do
    OUTPUT="llama-3.1-8b-${QUANT,,}.gguf"
    ./llama-quantize --imatrix $IMATRIX $MODEL $OUTPUT $QUANT
    echo "Created: $OUTPUT ($(du -h $OUTPUT | cut -f1))"
done

from llama_cpp import Llama

# Load model
llm = Llama(
    model_path="./model-q4_k_m.gguf",
    n_ctx=4096,          # Context window
    n_gpu_layers=35,     # GPU offload (0 for CPU only)
    n_threads=8          # CPU threads
)

# Generate
output = llm(
    "What is machine learning?",
    max_tokens=256,
    temperature=0.7,
    stop=["</s>", "\n\n"]
)
print(output["choices"][0]["text"])

from llama_cpp import Llama

llm = Llama(
    model_path="./model-q4_k_m.gguf",
    n_ctx=4096,
    n_gpu_layers=35,
    chat_format="llama-3"  # Or "chatml", "mistral", etc.
)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is Python?"}
]

response = llm.create_chat_completion(
    messages=messages,
    max_tokens=256,
    temperature=0.7
)
print(response["choices"][0]["message"]["content"])

from llama_cpp import Llama

llm = Llama(model_path="./model-q4_k_m.gguf", n_gpu_layers=35)

# Stream tokens
for chunk in llm(
    "Explain quantum computing:",
    max_tokens=256,
    stream=True
):
    print(chunk["choices"][0]["text"], end="", flush=True)

# Start server
./llama-server -m model-q4_k_m.gguf \
    --host 0.0.0.0 \
    --port 8080 \
    -ngl 35 \
    -c 4096

# Or with Python bindings
python -m llama_cpp.server \
    --model model-q4_k_m.gguf \
    --n_gpu_layers 35 \
    --host 0.0.0.0 \
    --port 8080

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8080/v1",
    api_key="not-needed"
)

response = client.chat.completions.create(
    model="local-model",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=256
)
print(response.choices[0].message.content)

# Build with Metal
make clean && make GGML_METAL=1

# Run with Metal acceleration
./llama-cli -m model.gguf -ngl 99 -p "Hello"

# Python with Metal
llm = Llama(
    model_path="model.gguf",
    n_gpu_layers=99,     # Offload all layers
    n_threads=1          # Metal handles parallelism
)

# Build with CUDA
make clean && make GGML_CUDA=1

# Run with CUDA
./llama-cli -m model.gguf -ngl 35 -p "Hello"

# Specify GPU
CUDA_VISIBLE_DEVICES=0 ./llama-cli -m model.gguf -ngl 35

# Build with AVX2/AVX512
make clean && make

# Run with optimal threads
./llama-cli -m model.gguf -t 8 -p "Hello"

# Python CPU config
llm = Llama(
    model_path="model.gguf",
    n_gpu_layers=0,      # CPU only
    n_threads=8,         # Match physical cores
    n_batch=512          # Batch size for prompt processing
)

# Create Modelfile
cat > Modelfile << 'EOF'
FROM ./model-q4_k_m.gguf
TEMPLATE """{{ .System }}
{{ .Prompt }}"""
PARAMETER temperature 0.7
PARAMETER num_ctx 4096
EOF

# Create Ollama model
ollama create mymodel -f Modelfile

# Run
ollama run mymodel "Hello!"

# Place in models folder
cp model-q4_k_m.gguf text-generation-webui/models/

# Start with llama.cpp loader
python server.py --model model-q4_k_m.gguf --loader llama.cpp --n-gpu-layers 35

# Use mmap for faster loading
./llama-cli -m model.gguf --mmap

# Reduce GPU layers
./llama-cli -m model.gguf -ngl 20  # Reduce from 35

# Or use smaller quantization
./llama-quantize model-f16.gguf model-q3_k_m.gguf Q3_K_M

# Always use imatrix for Q4 and below
./llama-imatrix -m model-f16.gguf -f calibration.txt -o model.imatrix
./llama-quantize --imatrix model.imatrix model-f16.gguf model-q4_k_m.gguf Q4_K_M