欢迎加入我们～
Common methods collection used by harmonyos drivers.
TLLM_QMM strips the implementation of quantized kernels of Nvidia's TensorRT-LLM, removing NVInfer dependency and exposes ease of use Pytorch module. We modified the dequantation and weight preprocessing to align with popular quantization alogirthms such as AWQ and GPTQ, and combine them with new FP8 quantization.
A highly optimized LLM inference acceleration engine for Llama and its variants.
最近更新: 5小时前TLLM_QMM strips the implementation of quantized kernels of Nvidia's TensorRT-LLM, removing NVInfer dependency and exposes ease of use Pytorch modul...
最近更新: 5小时前Presto Connectors project has been moved to TiBigData at PingCAP Incubator
最近更新: 5小时前Arcanist is the CLI to Differential, Facebook's code review tool. Currently an unstable preview release.
最近更新: 5小时前An efficient and effective learning to rank algorithm by mining information across ranking candidates. This repository contains the tensorflow impl...
最近更新: 6小时前