chiennv2000/orthrus
[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
$ git clone https://github.com/SafeAILab/EAGLE.git[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.
▲ +63 ★ this week
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
▲ +4 ★ this week
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
▲ +16 ★ this week
High-speed Large Language Model Serving for Local Deployment
▲ +10 ★ this week
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
▲ +5 ★ this week
A high-performance inference engine for LLM, VLM and DiT models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.
Data from GitHub · snapshot Nov 16, 2026