Highlights
- Pro
Stars
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
A high-throughput and memory-efficient inference and serving engine for LLMs
🔥 single-command flamegraph profiling 🔥
eBPF distributed networking observability tool for Kubernetes
🦀 How to minimize Rust binary size 📦
A Library for Advanced Deep Time Series Models.
About Code release for "TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis" (ICLR 2023), https://openreview.net/pdf?id=ju_Uqw384Oq
BCC - Tools for BPF-based Linux IO analysis, networking, monitoring, and more
《Hello 算法》:动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新,English version ongoing
Scaffolding for BPF application development with libbpf and BPF CO-RE
AISystem 主要是指AI系统,包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
Glances an Eye on your system. A top/htop alternative for GNU/Linux, BSD, Mac OS and Windows operating systems.
A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.
Dynolog is a telemetry daemon for performance monitoring and tracing. It exports metrics from different components in the system like the linux kernel, CPU, disks, Intel PT, GPUs etc. Dynolog also …
Userspace eBPF runtime for Observability, Network & General Extensions Framework
Automated upstream mirror for libbpf stand-alone build.
An open-source UI-first Identity and Access Management (IAM) / Single-Sign-On (SSO) platform with web UI supporting OAuth 2.0, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, RADIUS, Goo…
The production-scale datacenter profiler (C/C++, Go, Rust, Python, Java, NodeJS, .NET, PHP, Ruby, Perl, ...)
A Holistic Memory Performance Metric for Cloud Computing
blazesym is a library for address symbolization and related tasks