GradientHQ/parallax
▲ +8 ★ this week
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
A high-performance inference engine for LLM, VLM and DiT models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.
$ git clone https://github.com/xLLM-AI/xllm.git▲ +8 ★ this week
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy [ICML 2026]
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
PyTorch library for cost-effective, fast and easy serving of MoE models.
▲ +132 ★ this week
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Data from GitHub · snapshot Nov 16, 2026