8000
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 efficie…
Scalable toolkit for efficient model reinforcement
SGLang is a high-performance serving framework for large language models and multimodal models.
VPS Fusion Monster Server Test GO Version Aiming to be the most comprehensive server testing project, implemented in Go with zero environment dependencies. VPS融合怪服务器测评项目 GO版本 尽量成为最全能的服务器测评项目,使用 Go …
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
A high-throughput and memory-efficient inference and serving engine for LLMs
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Evaluating Large Language Models for CUDA Code Generation ComputeEval is a framework designed to generate and evaluate CUDA code from Large Language Models.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
CUDA Library Samples
NeMo: a toolkit for conversational AI
Perf monitoring CLI tool for Apple Silicon
Efficient Distributed GPU Programming for Exascale, an SC/ISC Tutorial
Learning Convolutional Neural Networks with Interactive Visualization.
cuDF - GPU DataFrame Library
High-performance TensorFlow library for quantitative finance.
http://nlp.seas.harvard.edu/2018/04/03/attention.html
Code & Data for "Tabular Transformers for Modeling Multivariate Time Series" (ICASSP, 2021)
Implementation of "Attention Is All You Need" using pytorch
Optimized primitives for collective multi-GPU communication
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
Source code examples from the Parallel Forall Blog
TensorFlow for macOS 11.0+ accelerated using Apple's ML Compute framework.
CUDA Python Low-level Bindings
FIL backend for the Triton Inference Server
An Aspiring Drop-In Replacement for NumPy at Scale