Training Experiment · Python

kvidcache

karims@karims · Atlas 67.7 · #7= builder

What it is

kvidcache is a research repository that investigates temporal redundancy in transformer KV caches by implementing and evaluating various predictors and codecs for residual compression.

Scored from the code at its last scan, 24 Oct 2026. How merit is scored

Where it counts

NLP & LLMs90%
Machine Learning80%
Data Science20%
Computer Vision10%
MLOps10%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the NLP & LLMs board

Whole board

RankProjectBuilderFieldMerit

12, shared rankdokturek-LightRAGLibrary / Framework · PythonThis repository provides a LightRAG library for Retrieval-Augmented Generation, including document processing, embedding, and querying capabilities. It also includes examples, tests, documentation, and deployment guides for building and deploying RAG applications.63.4/100AdvancedPetr SovadinaNLP & LLMs
12, shared rankEuchreGameDataset / Data Pipeline · PythonThe EuchreGame repository provides a deterministic Python Euchre engine, a browser-based sandbox for gameplay and AI interaction via Pyodide, and a data factory pipeline for generating synthetic trajectories to distill a language model into a Euchre-playing agent.63.4/100AdvancedJarad PeckenpaughNLP & LLMs
14kvidcacheTraining Experiment · Python62.7/100AdvancedkarimsNLP & LLMs
15proofmarkAI Developer Tool · Pythonproofmark is a Python library that provides a validation and repair pipeline for structured JSON generated by large language models. It includes deterministic normalization, application-level checks, and a tiered retry mechanism to minimize costly LLM calls.62.2/100AdvancedkarimsNLP & LLMs
16llmastsearchAI Developer Tool · RustThe llmastsearch project is a Rust-based command-line tool and library for performing syntax-aware code queries using tree-sitter parsers, providing structured JSON output optimized for LLM consumption. It supports seven programming languages and includes features such as…62.0/100AdvancedLuiz Cesar SpiesNLP & LLMs

What it is

Where it counts

Around it on the NLP & LLMs board

More from karims