Zero Bubble Pipeline Parallelism

A lecture note for understanding deep learning

上海交通大学抢课脚本（2020临时版本更新）

unlocks the 60 fps cap

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Distributed Training Over-The-Internet

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 utilizatio…

FlagScale is a large model toolkit based on open-sourced projects.

A library to analyze PyTorch traces.

A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

Tutel MoE: An Optimized Mixture-of-Experts Implementation

A fast communication-overlapping library for tensor parallelism on GPUs.

Implementation of a parallel least squares support vector machine using multiple backends for different GPU vendors.

An OAI compatible exllamav2 API that's both lightweight and fast

A fast inference library for running LLMs locally on modern consumer-class GPUs

学园偶像大师助手 | Assistant For Gakuen Idolmaster/学園アイドルマスター/学マス

AI for MAA

ThunderSVM: A Fast SVM Library on GPUs and CPUs

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

downloader using selenium for iwara

Process-aware, eBPF-based tcpdump

Passive ping network monitoring utility (C++)

Making eBPF programming easier via build env and examples

A curated list of awesome projects related to eBPF.

Mitsuba 3: A Retargetable Forward and Inverse Renderer