Files
vLLM/vllm/model_executor/layers/quantization/turboquant/quantizer.py
T

7 lines
223 B
Python

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""TurboQuant quantizer utilities.
Triton kernels handle all quantization, packing, and dequantization on GPU.
"""