Noureddine RAMDI Dinour

vLLM Compressor applies advanced quantization and compression techniques to large language models, enabling optimized inference without requiring full model definitions.

LiteRT-LM is a Google AI Edge C++ library for performant language model inference on edge devices with multi-language API support and easy CLI usage.

Lucebox Hub optimizes LLM inference on consumer GPUs using a megakernel CUDA approach and speculative decoding, achieving high throughput on RTX 3090 and newer Nvidia GPUs.

Explore a comprehensive LLM course with practical notebooks on fine-tuning (QLoRA, DPO), quantization (GPTQ), and tools like AutoEval and LazyMergekit. Ideal for aspiring LLM engineers.

LlamaFactory offers a modular Python framework for fine-tuning 100+ LLMs with diverse algorithms and optimizations, including LoRA, QLoRA, and reinforcement learning.