4594e6faba
This change adds support for Marlin-quantized models. Marlin is an FP16xINT4 matmul kernel, which provides good speedups decoding batches of 16-32 tokens. It supports quantized models with symmetric quantization, groupsize -1 or 128, and 4-bit. Tested with: - Llama 2 - Llama 3 - Phi 3 |
||
|---|---|---|
| .. | ||
| images | ||
| models | ||
| conftest.py | ||
| poetry.lock | ||
| pyproject.toml | ||
| pytest.ini | ||
| requirements.txt | ||