LLM Admission Gateway — Reserve, Commit, Expire
A rate limiter for inference traffic, where cost is tokens rather than requests and the dominant part of that cost is u…
Building the future, one commit at a time. Here are some of my open-source projects and research work.
A rate limiter for inference traffic, where cost is tokens rather than requests and the dominant part of that cost is u…
Multi-scalar multiplication eats 60–70% of Halo2 proving time. hanfei-shu moves it to the GPU: 3.3–4.8× over single-thr…
One command verifies every reference in a .bib file against five scholarly databases, catching phantom DOIs, fabricated…
An event-driven C++20 trading engine built around a hard boundary between a nanosecond fast path and an LLM-scale slow …
14 interactive self-study projects unified under a shared Python framework — 854 exercises across economics, physics, G…
A non-invasive debugging framework for multi-agent LLM systems that reconstructs causal fault graphs from execution log…
Visual neural architecture search: drag-and-drop NN builder with SHAP/Fisher-guided NAS and evolutionary search in ~480…
Historical narrative conflict detection using BM25 + knowledge graphs + belief graph reasoner, in preparation for ACL R…
Distributed multi-agent coordination runtime with actor model, AST-based conflict detection, backpressure, and circuit …