Pinned Loading

1. inferplan inferplan Public

   Plan LLM deployments before you buy the GPUs. Client-side calculators for inference memory, multi-GPU sharding, training/fine-tuning, and llm-d prefill/decode fleet sizing to latency SLOs — one aud…

   TypeScript 1

2. inferlens inferlens Public

   Engine-neutral observability for LLM inference engines — a pip-installed vLLM plugin that records scheduler decisions, KV-cache behavior, and per-request queued→prefill→decode timing as an interact…

   Python 2

3. kvault kvault Public

   Searchable knowledge corpus with BM25 ranking. Rust library, CLI, and MCP server.

   Rust 2

4. nvim-dap-memview nvim-dap-memview Public

   Memory viewer (live hex dump) for nvim-dap — DAP readMemory with changed-byte highlighting

   Lua 2