JustVugg / nanoeuler
GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.
Why this job: says: from scratch
What it does
With step size Δt = 1 this is exactly the residual update. So a deep residual network is a *discretized ODE*: depth is integration time, and each layer integrates the hidden state forward by one Euler step. This is the view behind work like Neural ODEs (a ResNet is the Euler discretization of a continuous flow). The project is named after Leonhard Euler, who gave us that integration method.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 4 months ago
- Stars
- 127
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Cuda
- 74% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| prabeakarve / microgpt | 51 | 5 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Cuda 74%
- C 23%
- Shell 3%
- Makefile <1%
Topics
- bpe-tokenizer
- byte-pair-encoding
- c
- cublas
- cuda
- deep-learning
- flashattention
- from-scratch
- gpt2
- language-model
- llm
- machine-learning
Project record
- JobLists and guides
- StatusListed
- Commits45
- Forks26
- Watching3
- Stars in 28 days+3
- CreatedJun 15, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026