text-generation-inference

4594e6fa - Add support for Marlin-quantized models

Add support for Marlin-quantized models 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