open-models

2 个项目 · ⭐ 32.4k

lyogavin/airllm

AirLLM 70B inference with single 4GB GPU

Jupyter Notebook ⭐ 32.2k ⑂ 3.4k Apache-2.0 · 18 小时前推送

chinese-llm chinese-nlp

18 小时前

最近推送

FonaTech/Project_Chronos

⚡ Zero-Stall MoE Inference via Lookahead Prediction & Async DMA Prefetching. Optimized for SSD I/O with Hybrid MLA+Sliding Window Attention.

Python ⭐ 203 ⑂ 21 Apache-2.0 · 2026-04-26推送

2026-04-26