Pinned Loading

1. dotfiles dotfiles Public

   Dotfiles for my macbook air.

   Vim Snippet 59 5

2. aoc2024 aoc2024 Public

   OCaml

3. core-latency core-latency Public

   CPU Latency Analysis Tools for Cloud VMs - A C++ toolkit for measuring and visualizing cache coherence operation latencies and TLB miss penalties in multi-core systems.

   C++

4. github-analysis github-analysis Public

   GitHub repository analysis CLI tool based on Model Context Protocol (MCP) client-server architecture and Qwen2.5 for AI-powered repository insights.

   Python

5. llama-chops llama-chops Public

   A Ray-based prefill-decode disaggregation system for efficient LLM inference. Separates prompt processing and token generation phases with KV-cache management, built on Llama 3.2.

   Python

6. pgvector pgvector Public

   Forked from pgvector/pgvector

   Open-source vector similarity search for Postgres

   C