---
title: "infinity vs LLMs-from-scratch"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/michaelfeil-infinity-vs-rasbt-llms-from-scratch"
tools: ["michaelfeil-infinity", "rasbt-llms-from-scratch"]
---

# infinity vs LLMs-from-scratch

*GraphCanon updated Jul 12, 2026*

## Verdict

Pick infinity if infinity is a high-throughput, low-latency serving engine that supports text-embeddings, reranking models, CLIP, CLAP, and ColPaLi, with GPU acceleration including ROCm and TensorRT; pick LLMs-from-scratch if 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.

[infinity](https://michaelfeil.github.io/infinity/) reports 2.9k GitHub stars, 196 forks, and 130 open issues, last pushed Mar 24, 2026. [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 [infinity's repository](https://github.com/michaelfeil/infinity) and [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch).

| | [infinity](/tools/michaelfeil-infinity.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) |
| --- | --- | --- |
| Tagline | High-throughput, low-latency serving engine for text-embeddings and various models | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step |
| Stars | 2,874 | 98,899 |
| Forks | 196 | 15,183 |
| Open issues | 130 | 4 |
| Language | Python | Jupyter Notebook |
| Adopt for | Infinity is a high-throughput, low-latency serving engine that supports text-embeddings, reranking models, CLIP, CLAP, and ColPaLi, with GPU acceleration including ROCm and TensorRT. | 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 | MIT | Other |
| Categories | Inference & Serving | LLM Frameworks, Model Training |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [infinity](/tools/michaelfeil-infinity.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) |
| --- | --- | --- |
| Maintenance | Slowing (36%) | Steady (60%) |
| Days since push | 109d | 38d |
| Open issues (now) | 130 | 4 |
| Full report | [trust report](/tools/michaelfeil-infinity/trust.md) | [trust report](/tools/rasbt-llms-from-scratch/trust.md) |

## Decision facts: infinity

- **Adopt for:** Infinity is a high-throughput, low-latency serving engine that supports text-embeddings, reranking models, CLIP, CLAP, and ColPaLi, with GPU acceleration including ROCm and TensorRT.

## 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 infinity if…

- infinity is primarily Python; LLMs-from-scratch is Jupyter Notebook.
- License: infinity is MIT, LLMs-from-scratch is Other.
- Tags unique to infinity: clap, clip, colpali, docker-container.
- Also covers Inference & Serving.
- When you need to serve embeddings and various models with high throughput and low latency.

### Choose LLMs-from-scratch if…

- LLMs-from-scratch is primarily Jupyter Notebook; infinity is Python.
- License: LLMs-from-scratch is Other, infinity is MIT.
- Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, deep-learning.
- Also covers LLM Frameworks, Model Training.
- - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.

## When NOT to use infinity

- Avoid using Infinity if your setup does not require GPU acceleration since its specialized Docker images may introduce unnecessary complexity.
- Do not use Infinity if you are working with models that are not supported by it (such as specific NLP models outside of embeddings and reranking).

## 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 infinity and LLMs-from-scratch?

infinity: High-throughput, low-latency serving engine for text-embeddings and various models. 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 infinity over LLMs-from-scratch?

Choose infinity over LLMs-from-scratch when infinity is primarily Python; LLMs-from-scratch is Jupyter Notebook; License: infinity is MIT, LLMs-from-scratch is Other; Tags unique to infinity: clap, clip, colpali, docker-container; Also covers Inference & Serving; When you need to serve embeddings and various models with high throughput and low latency.

### When should I choose LLMs-from-scratch over infinity?

Choose LLMs-from-scratch over infinity when LLMs-from-scratch is primarily Jupyter Notebook; infinity is Python; License: LLMs-from-scratch is Other, infinity is MIT; Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, deep-learning; Also covers LLM Frameworks, Model Training; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.

### When should I avoid infinity?

Avoid using Infinity if your setup does not require GPU acceleration since its specialized Docker images may introduce unnecessary complexity. Do not use Infinity if you are working with models that are not supported by it (such as specific NLP models outside of embeddings and reranking).

### 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 infinity or LLMs-from-scratch more popular on GitHub?

LLMs-from-scratch has more GitHub stars (98,899 vs 2,874). Stars measure visibility, not whether either tool fits your constraints.

### Are infinity and LLMs-from-scratch open source?

Yes - both are open-source projects on GitHub (infinity: MIT, LLMs-from-scratch: Other).

### Where can I find alternatives to infinity or LLMs-from-scratch?

GraphCanon lists graph-backed alternatives at [infinity alternatives](/tools/michaelfeil-infinity/alternatives) and [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) ([infinity markdown twin](/tools/michaelfeil-infinity/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/michaelfeil-infinity-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, infinity or LLMs-from-scratch?

infinity: Slowing. 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 infinity and LLMs-from-scratch?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [infinity trust report](/tools/michaelfeil-infinity/trust); [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=michaelfeil-infinity`](/api/graphcanon/graph?tool=michaelfeil-infinity)
- 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/_