Star 总榜

Docker&vLLM官方镜像部署DeepSeek模型，在生产环境中提供类OpenAI接口服务。

A lean, local AI research agent framework that runs on your machine

GLM-5.2 744B with a true 4-bit NVFP4 KV cache on 4x DGX Spark: 42 tok/s peak, 317K-token KV pool (+58.6% vs fp8), needle-verified at 250K depth, serving 316K context

Running Large Language Model easily.

Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.

Reproducible recipe: serve abliterated Gemma-4-12B (gemma4_unified) at 50-118 tok/s on no-NVLink Blackwell (SM120) via vLLM nightly + ModelOpt FP8/NVFP4 + MTP spec-decode.

An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source LLM (Qwen2.5-Coder) on vLLM, with AddressSanitizer as a ground-truth oracle.

FlashAttention-style custom attention backend for vLLM on AMD MI50/MI60/Radeon VII (gfx906). Downstream fork of mixa3607/ML-gfx906 with replacement HIP kernels and a vllm.general_plugins entry point.

This Russia Doesn't Exist

Madlab is an advanced AI development studio designed to streamline the process of dataset management, model training, and evaluation. It combines a robust Node.js/Express backend with a powerful Python-based training engine and a modern React frontend.

Fine-tuned LLM for electroencephalography(EEG) data classification

HypeLoRA: Hypernetwork-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning

CosyVoice3 LoRA fine-tuning companion repo — PEFT integration, 9 known pitfalls from IMDA NSC production runs, corrected from failed full-SFT attempt

Kairos: An autonomous development supervisor powered by Context Engineering. It provides a living memory and a contextual constitution for your projects to prevent AI context loss.

Tool for auto-generating README documentation for code repositories

LoRA supervised fine-tuning, RLHF (PPO) and RAG with llama-3-8B on the TLDR summarization dataset

An application that summarizes and classifies long text using zero-shot transfer-learning hosted on Huggingface spaces.

Verified multi-source distribution for local LLM weights

预训练模型知识量度量竞赛 Baseline F1 0.35 BERTForMaskedLM

Finetune Web UI is a user-interface for training and deploying pre-trained models.