Stars
Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
[Reproduction] Inference Time Scaling for Generalist Reward Modeling
A benchmark for LLMs on complicated tasks in the terminal
[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
A Model Control Protocol (MCP) server that allows Claude to communicate with locally running LLM models via LM Studio.
Model Context Protocol Servers
[NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting"
HOU-SZ / EyecareGPT
Forked from DCDmllm/EyecareGPTOfficial Repo for Paper ‘’EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model‘’
Official Repo for Paper ‘’EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model‘’
【ICML 2025 Spotlight】 Official Repo for Paper ‘’HealthGPT : A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation‘’
Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
✨✨Latest Advances on Multimodal Large Language Models
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA etc.🔥
A high-throughput and memory-efficient inference and serving engine for LLMs
HiAE - A High-Throughput Authenticated Encryption Algorithm for Cross-Platform Efficiency.
HAKES: Efficient Data Search with Embedding Vectors at Scale
Benchmarks of approximate nearest neighbor libraries in Python
[EMNLP 2024] CryptoTrade: A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading https://aclanthology.org/2024.emnlp-main.63.pdf
Official implementation of paper "HiAE: A High-Throughput Authenticated Encryption Algorithm for Cross-Platfor Efficiency"
[NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*
Serverless LLM Serving for Everyone.
[NIPS'24] UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis