GitHub

Pinned Loading

  1. High-performance GPU kernels for LLM inference in OpenAI Triton. Fused RMSNorm, SwiGLU, INT8 GEMM with benchmarks and roofline analysis.

    Python 39 7

  2. Evolutionary adversarial testing framework for AI safety using quality-diversity search to discover interpretable, transferable vulnerabilities across LLMs. (ICLR 2026)

    Rust 3 1

  3. Compile REST/OpenAPI and SOAP/WSDL services into governed MCP tool surfaces: provenance on every field, policy derived separately from code, and a human approval gate before any write or destructiv…

    Python

  4. Spark-native LLM evaluation framework with confidence intervals, significance testing, and Databricks integration

    Python 6

  5. Runtime control of LLM agent behaviors through activation steering vectors. More calibrated than prompting.

    Python 8

  6. Modern ISO 8583 simulator with CLI, Python SDK, and interactive notebooks. Parse/build/validate messages at 180k+ TPS. Supports all major card networks and EMV chip data.

    Python 51 20

Read the original on github.com ↗