This page is generated automatically from @0xSero's public GitHub activity. It is not run, verified or endorsed by @0xSero or by GitHub, and DevTrack never asks for a GitHub password.
Unclaimed profile
If you are @0xSero, sign in with GitHub as @0xSero to claim it: join the leaderboard, keep your 143,020 XP and tier, count private contributions, and get README badges. Only the owner of the GitHub account can claim it.
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
Your AI friend right in your browser
Built from public GitHub data and refreshed every few hours. Not affiliated with @0xSero.
Dot-lattice art: photo to two-tone dot map to seamless animated loop (engine + scripts)
Ship your repo + live coding-agent session (Claude Code / Codex / pi / Droid) to another machine over Tailscale; it resumes in tmux and keeps working.
Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache