optimization

Multi-Faceted AI Agent and Workflow Autotuning. Automatically optimizes LangChain, LangGraph, DSPy programs for better quality, lower execution latency, and lower execution cost. Also has a simple agent/workflow framework

One file. Your AI coding agent becomes a scientist. 30+ experiments while you sleep.

An Automated AI-Powered Prompt Optimization Framework

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

Data Center and Client workload and software optimizations for Intel hardware.

An algorithm-focused interface for common llm training, continual learning, and reinforcement learning techniques

Repository for the companion Colab notebook of the Domain-Specific Small Language Models book.

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

LLM Optimize is a proof-of-concept library for doing LLM (large language model) guided blackbox optimization.

reference pytorch code for intent classification

[IEEE TGRS 2025] Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices

Automatically benchmark and optimize attention in diffusion models. 1.5-2x speedup on RTX 4090.

Learning PyTorch through the D2L book. A series of notebooks for the same

Set of fast LINQ-like extension methods for arrays and lists. Fine-tune your code for the maximum performance.

Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.

Code and supplementary materials for the research paper titled 'Advancing Geological Image Segmentation: Deep Learning Approaches for Rock Type Identification and Classification', published in Applied Computing and Geosciences (Elsevier).

A LLaMA2-7b chatbot with memory running on CPU, and optimized using smooth quantization, 4-bit quantization or Intel® Extension For PyTorch with bfloat16.

An optimized FastAPI server for OpenAI's Whisper whisper-large-v3-turbo model using MLX optimization

Code the ICML 2024 paper: "Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models"

FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference