Books
- Unsloth: Efficient Fine-Tuning for Large Language ModelsMethods and Workflows for Fine-Tuning and Deploying Large Language Models on Limited HardwareEdgar Milvus
Master the engineering principles behind Unsloth to fine-tune Large Language Models on limited hardware. Discover technical workflows for 4-bit quantization, custom Triton kernels, and Direct Preference Optimization. This guide covers the full lifecycle, including context expansion and production deployment via GGUF and vLLM. A rigorous reference for developers seeking to maximize LLM performance on consumer-grade GPUs.
A builder's guide to AI-powered performance testing, from a multi-agent platform that turns 25 minutes of manual correlation into 75 seconds, written by the engineer who built it.
