Peng Tao's repositories
kata-containers
Kata Containers is an open source project and community working to build a standard implementation of lightweight Virtual Machines (VMs) that feel and perform like containers, but provide the workload isolation and security advantages of VMs. https://katacontainers.io/
DeepLearningSystem
Deep Learning System core principles introduction.
firecracker
Secure and fast microVMs for serverless computing.
grok-1
Grok open release
iree
A retargetable MLIR-based machine learning compiler and runtime toolkit.
Liger-Kernel
Efficient Triton Kernels for LLM Training
llm-inference-solutions
A collection of all available inference solutions for the LLMs
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
MS-AMP
Microsoft Automatic Mixed Precision Library
open-gpu-kernel-modules
NVIDIA Linux open GPU kernel module source
PancrePal-xiaoyibao
面向胰腺癌肿瘤患者的智能RAG平台
qserve
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
tag-runtime
🏃🏿♀️🏃🏽♀️🏃🏻♂️🕒CNCF Technical Advisory Group for Runtime
ThunderKittens
Tile primitives for speedy kernels
TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
triton
Development repository for the Triton language and compiler
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs