Language Models
ZinYY/AdaFlash
[COLMW'26 Spotlight] AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters
Pythonno licenseupdated Oct 28, 2026
[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.
$ git clone https://github.com/chiennv2000/orthrus.git[COLMW'26 Spotlight] AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters
[ICML 2026] When Drafts Evolve: Speculative Decoding Meets Online Learning
▲ +60 ★ 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.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
▲ +13 ★ this week
High-speed Large Language Model Serving for Local Deployment
▲ +7 ★ this week
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
Data from GitHub · snapshot Nov 13, 2026