flashserve

Pinned Loading

1. PAT PAT Public

   Prefix-Aware Attention for LLM Decoding

   Python 48 3

2. RAGPulse RAGPulse Public

   An Open-Source RAG Workload Trace to Optimize RAG Serving Systems

   Python 40 4

3. flash-linear-attention-npu flash-linear-attention-npu Public

   C++ 48 62