A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.
- learning-resources
- llm
- llm-inference
- mlops
111,821 visible repositories in the index
27,193–27,216 of 52,734 · Most stars
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.
:fish::fish::fish: 机器学习面试复习资源
linux内核网络协议栈源码阅读分析注释--带详尽中文分析注释以及相关流程分析调用注释,对理解分析内核协议栈源码很有帮助
Convenience methods for creating color using RGBA hex string.
Log-based transactional graph engine
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
Boosting your Web Services of Deep Learning Applications.
Tracks is a GTD™ web application, built with Ruby on Rails
Community Mod editor/creator for REDengine games.
An all-in-one tool that lets you easly manage BeatSaber versions, maps, mods, and even more.
:wave: Touch gesture library, 1kb~5kb, compatible with PC / mobile
Stop half-done APIs! Cherrybomb is a CLI tool that helps you avoid undefined user behaviour by auditing your API specifications, validating them and running API security tests.
[CVPR 2026] 🔥🔥 Official Repo of USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning
A database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonomous AI agents
Now part of Hasura GraphQL Engine. Listen to postgres events and forward them as JSON payloads to a webhook
A new, render-graph based 3D game engine for Linux and Windows using C++20 and Vulkan API 1.3 (in early development)
📜 Create mutable log lines into the terminal, and give life to your logs!
A Java library for capturing, crafting, and sending packets.
Real time emotion recognition
SwissGL is a minimalistic wrapper on top of WebGL2 JS API. It's designed to reduce the amount of boilerplate code required to manage GLSL shaders, textures and framebuffers when making procedural visualizations or simulations.
A professional list on Large (Language) Models and Foundation Models (LLM, LM, FM) for Time Series, Spatiotemporal, and Event Data.
Use native tab discarding method to automatically reduce memory usage of inactive tabs
High performance ping tool
Make Prettier organize your imports using the TypeScript language service API.