KVarN: Native vLLM backend for KV-cache quantization by Huawei(github.com)

134 points by theanonymousone 4 months ago | 13 comments

Show HN: Cachekit – High performance caching policies library in Rust(github.com)

41 points by failsafe 9 months ago | 7 comments

Show HN: Agentic CUDA Kernel Optimizer(github.com)

29 points by bertaye 1 month ago | 6 comments

GitHub repository for a LangGraph-based agentic workflow that uses a C++ CUDA test harness to benchmark, profile, and optimize CUDA kernels.

Show HN: Kern – container and resource runtime in a 1.5 MB binary, no daemon(github.com)

45 points by realexweb 2 months ago | 6 comments

Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep(github.com)

415 points by Bibabomas 5 months ago | 137 comments

GitHub repository for Semble, an open-source CPU-based code search tool and MCP server for AI coding agents combining static embeddings with BM25.

Show HN: Claude-thermos keeps your Claude session warm for you(github.com)

94 points by s0ck_r4w 3 months ago | 77 comments