tommasocerruti / linear-attention-architectures Star 22 Code Issues Pull requests Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing (Technical Report) associative-memory delta-net attention-mechanisms linear-attention efficient-attention kimi-linear gated-deltanet Updated Jul 10, 2026 Python
neosun100 / kimi-linear-vllm-docker-serve Star 2 Code Issues Pull requests Dockerized vLLM serving for Kimi-Linear-48B-A3B (AWQ-4bit), from 128K to 1M context. docker awq long-context llm-serving vllm kimi-linear Updated Jul 13, 2026 Python
Soumadeep03052001 / Kimi-Linear Star 0 Code Issues Pull requests 🚀 Explore Kimi Linear, an efficient attention architecture designed for expressive performance in natural language processing tasks. docker awq long-context llm-serving vllm kimi-linear Updated Jul 15, 2026 HTML