🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
- artificial-intelligence
- deep-learning
- optimizers
- evolutionary-search
99,825 visible repositories in the index
121–144 of 290 · Most stars
🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
Awesome machine learning for combinatorial optimization papers.
Keras + Hyperopt: A very simple wrapper for convenient hyperparameter optimization
A best practices guide for day 2 operations, including operational excellence, security, reliability, performance efficiency, and cost optimization.
Differentiable convex optimization layers
AgentFlow: In-the-Flow Agentic System Optimization
EPUB to audiobook converter, optimized for Audiobookshelf, WebUI included
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
A manually tuned font revision of Readerly, with reduced and altered serifs, optimized for digital reading and e-readers. OFL licensed.
A library for differentiable nonlinear optimization
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
CUDA Accelerated Robot Library
OpenLane is an automated RTL to GDSII flow based on several components including OpenROAD, Yosys, Magic, Netgen and custom methodology scripts for design exploration and optimization.
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
SAM: Sharpness-Aware Minimization (PyTorch)
Physical Symbolic Optimization
The repository host gives no description.
A program for financial portfolio management, analysis and optimisation.
Open Source Pricing & Packaging Infrastructure
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
A Modular Toolkit for Robot Kinematic Optimization
AI on the way. An auto deep learning pipe dream. An RDBMS approach to deep learning. Declarative, explainable, scalable, optimizable, easy to deploy, all that good stuff.
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
PyTorch Extension Library of Optimized Scatter Operations