Pinned Loading

1. speculative-decoding speculative-decoding Public

   Reference implementation of LLM inference acceleration techniques. Includes speculative decoding, tree speculation, EAGLE, Medusa, KV-cache compression, and diffusion model efficiency with roofline…

   Python

2. spark-llm-eval spark-llm-eval Public

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

   Python 2

3. triton-kernels triton-kernels Public

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

   Python

4. steering-vectors-agents steering-vectors-agents Public

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

   Python

5. ai-metacognition-toolkit ai-metacognition-toolkit Public

   Python toolkit for detecting and analyzing metacognitive capabilities in AI systems. Includes situational awareness detection, counterfactual CoT analysis, and production monitoring.

   Python 1

6. LLMConsent/llmconsent-standards LLMConsent/llmconsent-standards Public

   LLMConsent is an open protocol that establishes standards for managing consent between humans and AI systems.

   1 1