A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
- speculative-decoding
132,218 visible repositories in the index
1,177–1,200 of 2,136 · Most stars
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.
The open, local take on Jev: typed decisions from an LLM, without generating a single token
Open source project for data preparation for GenAI applications
Open-source LLM gateway in Rust. One endpoint for OpenAI, Anthropic, Gemini and every other vendor. Any SDK, any model, any tool.
AgentSims is an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in.
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
Gemini web → OpenAI-compatible + native Gemini API, self-hosted, no API key. Gemini 4 Argon from a paid account cookie, strict_model (429 instead of a silent downgrade), cookie pool with auto-renewal, proxy pool, admin panel, image & video generation, single Go binary · 把 Gemini 网页反代成 OpenAI 兼容 / Gemini 原生 API,付费号 cookie 直接用 4 Argon
A privacy-first guardrail for LLMs and RAG pipelines. SurrogateShield detects, redacts, and reconstructs sensitive PII data on the fly while defending against adversarial attacks.
[中文法律大模型] DISC-LawLLM: an intelligent legal system powered by large language models (LLMs) to provide a wide range of legal services.
A scalable inference server for models optimized with OpenVINO™
RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.
See what your coding agent (Claude Code, Codex, Kimi) sends to the model — local proxy + web dashboard
Open-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.
An open-source version to use all the Models for free
LLM 逆向工程接口管理 | 通过标准 OpenAI API 访问 ChatGPT / gpt4free / Bard / Claude / HuggingChat / 通义千问 等 AI 的破解版 || ChatGPT reverse engineering API management | Access all reverse engineered LLM libs by standard OpenAI API format || 免费 ChatGPT Free GPT LLM API | 逆向工程 转 OpenAI API | converts all llm libs to OpenAI API
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Claude Agent SDK
Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks
Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.
An easy-to-use Python framework to generate adversarial jailbreak prompts.
md/html 双向流水线 · 三个能力一站式:万物→md / md→精美html / html→md。封装 markitdown + Pandoc + html-to-markdown + trafilatura。4 套反 AI slop 主题。Claude Code skill.
Code for the Molmo Vision-Language Model