Libraries & frameworks
tinyengram
autoark/tinyengram
Open research codebase reproducing DeepSeek-style Engram memory-injection architecture on Qwen-3 and Stable Diffusion, comparing against LoRA fine-tuning with training experiments and vision extensions.
Topics
Related projects
Soup10.5kA one-config CLI framework for fine-tuning and post-training LLMs with QLoRA, evals, and export.
sglang38.7kA fast open-source inference framework for serving large language and multimodal models at scale.
FastGPT30kA visual low-code platform for building knowledge-based AI agents with RAG retrieval, workflows, plugins, and MCP.
tokenspeed2.9kA blazing-fast open-source LLM inference engine tuned for agentic workloads, pairing TensorRT-class speed with vLLM-like ease for production deployments at scale.
jackrong-llm-finetuning-guide1.7kAn educational knowledge base for LLM fine-tuning with training recipes, distillation workflows, dataset catalogs, and deployment guides.
can-i-finetune-this795A practical planning tool that estimates whether a Hugging Face model fits your GPU for fine-tuning, with memory breakdowns and runnable recipes.