Show HN: TurboGPT: train 22KiB transformer in 13s
turboGPT Tiny byte-level GPT training in CUDA C++. Build Windows, Visual Studio 2022 C++ tools, and CUDA 13.4: .\build.ps1 -CudaArch 86 CudaArch is the GPU compute capability from NVIDIA's CUDA GPU list. Run .\build\turbogpt.exe --data hn1g.txt --log-to runs/ctx4 The run stores its checkpoint at runs/ctx4/ctx4.pt, containing model, optimizer, scheduler, and trainer state.
- ▪turboGPT Tiny byte-level GPT training in CUDA C++.
- ▪Build Windows, Visual Studio 2022 C++ tools, and CUDA 13.4: .\build.ps1 -CudaArch 86 CudaArch is the GPU compute capability from NVIDIA's CUDA GPU list.
- ▪Run .\build\turbogpt.exe --data hn1g.txt --log-to runs/ctx4 The run stores its checkpoint at runs/ctx4/ctx4.pt, containing model, optimizer, scheduler, and trainer state.
Hacker News (Front Page) files mainly under programming. We currently carry 2,289 of its stories. Top-voted stories on Hacker News.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/lostmsu/TurboGPT |
| Publication time | Tue, 29 Sep 2026 19:20:02 +0000 |
| Retrieval time | 2026-09-29T20:42:33.835Z |
| Last seen | 2026-09-29T20:42:33.835Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | Vum_ycn1ORVz · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
turboGPT Tiny byte-level GPT training in CUDA C++. MIT. Build Windows, Visual Studio 2022 C++ tools, and CUDA 13.4: .\build.ps1 -CudaArch 86 CudaArch is the GPU compute capability from NVIDIA's CUDA GPU list. Run .\build\turbogpt.exe --data hn1g.txt --log-to runs/ctx4 The run stores its checkpoint at runs/ctx4/ctx4.pt, containing model, optimizer, scheduler, and trainer state. Use --load CHECKPOINT.pt to resume it. runs/ctx4/report.json is derived from the log directory. Logs are TensorBoard-compatible: one report per batch, capped at 8Mi reports, and flushed with periodic or final checkpoints. Result hn1g after 1.5G training tokens: 2.52435 BPB. Tests python tests\verify.py
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.