AI-Hypercomputer/JetStream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Model https://arxiv.org/pdf/2411.02433
$ git clone https://github.com/JayZhang42/SLED.gitJetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
▲ +13 ★ this week
High-speed Large Language Model Serving for Local Deployment
▲ +1 ★ this week
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
▲ +51 ★ this week
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.
中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3
Data from GitHub · snapshot Nov 13, 2026