Perkz Zheng

PerkzZheng/prims-ts-examples

Standalone examples for FlashInfer PrimTS attention APIs

PerkzZheng/flashinfer-prims-ts-validation

Reproducible accuracy and performance regression suite for FlashInfer PrimTS attention kernels

PerkzZheng/flashinfer-k3

Private FlashInfer K3 MLA development repository

PerkzZheng/FlashMLA-PR

FlashMLA: Efficient Multi-head Latent Attention Kernels

PerkzZheng/FlashMLA

PerkzZheng/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

PerkzZheng/flashinfer

FlashInfer: Kernel Library for LLM Serving

PerkzZheng/TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

PerkzZheng/cutlass

CUDA Templates for Linear Algebra Subroutines

PerkzZheng/fastertransformer_backend

PerkzZheng/apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

PerkzZheng/FasterTransformer

Transformer related optimization, including BERT, GPT

PerkzZheng/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

PerkzZheng/server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

PerkzZheng/flink-mnist

Run MNIST inference in Apache Flink

PerkzZheng/compilations

This repository contains compilation of some chosen topics.