scaleDown AI: Enterprise Model Quantization Platform Slash inference costs by 70%. Deploy LLMs anywhere. A microservices-based orchestration engine for isolating and automating incompatible AI optimization workflows.
Embeddable Python Engine for VibeVoice TTS with AWQ-INT4 quantization (50% VRAM, 2x Faster RTF) of VibeVoice Large 7B model
A from-scratch implementation of Llama-3.2-1B in PyTorch, decode-latency benchmarks on three GPUs (T4, L4, A100), and weight-only quantization (RTN and GPTQ) measured against both.
Fine-tuning pipeline for Qwen2.5-Coder-1.5B using QLoRA, DPO alignment, and AWQ quantization on free-tier Colab GPU.
Add a description, image, and links to the awq-quantization topic page so that developers can more easily learn about it.
To associate your repository with the awq-quantization topic, visit your repo's landing page and select "manage topics."