--- title: "MPP-LLaVA vs LLMs-from-scratch" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/coobiw-mpp-llava-vs-rasbt-llms-from-scratch" tools: ["coobiw-mpp-llava", "rasbt-llms-from-scratch"] --- # MPP-LLaVA vs LLMs-from-scratch *GraphCanon updated Jul 11, 2026* ## Verdict Pick MPP-LLaVA when tags unique to MPP-LLaVA: deepspeed, fine-tuning, mllm, model-parallel; pick LLMs-from-scratch when tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, deep-learning. [MPP-LLaVA](https://github.com/Coobiw/MPP-LLaVA) reports 683 GitHub stars, 34 forks, and 9 open issues, last pushed Mar 10, 2025. [LLMs-from-scratch](https://amzn.to/4fqvn0D) has 99k stars, 15k forks, and 4 open issues, last pushed Jun 2, 2026. Figures are from public GitHub metadata via [MPP-LLaVA's repository](https://github.com/Coobiw/MPP-LLaVA) and [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch). | | [MPP-LLaVA](/tools/coobiw-mpp-llava.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | | --- | --- | --- | | Tagline | Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Train | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | | Stars | 683 | 98,899 | | Forks | 34 | 15,183 | | Open issues | 9 | 4 | | Language | Jupyter Notebook | Jupyter Notebook | | Adopt for | - | LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions. | | Persona | - | - | | Runtime | - | - | | License | - | Other | | Categories | Computer Vision, LLM Frameworks, Model Training | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [MPP-LLaVA](/tools/coobiw-mpp-llava.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Steady (60%) | | Days since push | 487d | 38d | | Open issues (now) | 9 | 4 | | Full report | [trust report](/tools/coobiw-mpp-llava/trust.md) | [trust report](/tools/rasbt-llms-from-scratch/trust.md) | ## Decision facts: LLMs-from-scratch - **Adopt for:** LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions. ## Choose when ### Choose MPP-LLaVA if… - Tags unique to MPP-LLaVA: deepspeed, fine-tuning, mllm, model-parallel. - Also covers Computer Vision. ### Choose LLMs-from-scratch if… - Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, deep-learning. - - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. - More GitHub stars (99k vs 683) - visibility, not fit. ## When NOT to use MPP-LLaVA - Last GitHub push was 488 days ago (dormant maintenance, Mar 10, 2025). Validate activity before betting a new project on MPP-LLaVA. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. - Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ## When NOT to use LLMs-from-scratch - - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰 - a deeper learning experience. ## Common questions ### What is the difference between MPP-LLaVA and LLMs-from-scratch? MPP-LLaVA: Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Train. LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. See the comparison table for live GitHub stats and shared categories. ### When should I choose MPP-LLaVA over LLMs-from-scratch? Choose MPP-LLaVA over LLMs-from-scratch when Tags unique to MPP-LLaVA: deepspeed, fine-tuning, mllm, model-parallel; Also covers Computer Vision. ### When should I choose LLMs-from-scratch over MPP-LLaVA? Choose LLMs-from-scratch over MPP-LLaVA when Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, deep-learning; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework; More GitHub stars (99k vs 683) - visibility, not fit. ### When should I avoid MPP-LLaVA? Last GitHub push was 488 days ago (dormant maintenance, Mar 10, 2025). Validate activity before betting a new project on MPP-LLaVA. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ### When should I avoid LLMs-from-scratch? - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰 a deeper learning experience. ### Is MPP-LLaVA or LLMs-from-scratch more popular on GitHub? LLMs-from-scratch has more GitHub stars (98,899 vs 683). Stars measure visibility, not whether either tool fits your constraints. ### Are MPP-LLaVA and LLMs-from-scratch open source? Yes - both are open-source projects on GitHub. ### Where can I find alternatives to MPP-LLaVA or LLMs-from-scratch? GraphCanon lists graph-backed alternatives at [MPP-LLaVA alternatives](/tools/coobiw-mpp-llava/alternatives) and [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) ([MPP-LLaVA markdown twin](/tools/coobiw-mpp-llava/alternatives.md), [LLMs-from-scratch markdown twin](/tools/rasbt-llms-from-scratch/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/coobiw-mpp-llava-vs-rasbt-llms-from-scratch.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, MPP-LLaVA or LLMs-from-scratch? MPP-LLaVA: Dormant. LLMs-from-scratch: Steady. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for MPP-LLaVA and LLMs-from-scratch? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [MPP-LLaVA trust report](/tools/coobiw-mpp-llava/trust); [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=coobiw-mpp-llava`](/api/graphcanon/graph?tool=coobiw-mpp-llava) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_