# deepseek-ai/DeepGEMM SLOC report

> As of 2026-10-21 (commit 5081f8513af5), deepseek-ai/DeepGEMM contains 13,756 total lines: 10,951 code, 1,053 comments, 1,752 blank, across 81 files in 7 languages (top: C++ Header 75.4%). Custom configuration (tests excluded, docs excluded, generated excluded). Counted with tokei via OctoCounts.

deepseek-ai/DeepGEMM has 10,951 source lines of code out of 13,756 total lines across 81 files, counted from the main ref at commit 5081f8513af5 by the OctoCounts tokei engine on 2026-10-21. The report is cached by commit, tokei version, and analysis options, so recounting the same revision returns exactly these numbers.

OctoCounts produced this report by resolving deepseek-ai/DeepGEMM to commit 5081f8513af5, downloading the repository source archive, and counting every source file with tokei, the open-source line counter written in Rust. The table below breaks the count down by programming language into files, total lines, code lines, comment lines, and blank lines, so the figures can be compared across languages and projects. Results are cached by commit, tokei version, and analysis options, so counting the same revision again reproduces exactly these numbers.

## Repository size insights

This is a medium-sized codebase by counted code lines. Code represents 79.6% of all lines, comments represent 7.7%, and the repository averages 135 code lines per file. C++ Header accounts for 75.4% of counted code.

| Language | Files | Lines | Code | Comments | Blanks |
| --- | ---: | ---: | ---: | ---: | ---: |
| C++ Header | 48 | 10,111 | 8,262 | 709 | 1,140 |
| Python | 25 | 3,212 | 2,503 | 189 | 520 |
| Shell | 4 | 139 | 108 | 13 | 18 |
| C++ | 1 | 49 | 33 | 7 | 9 |
| CMake | 1 | 34 | 24 | 3 | 7 |
| CUDA | 1 | 36 | 21 | 7 | 8 |
| Markdown | 1 | 175 | 0 | 125 | 50 |

Top language (C++ Header 75.4%). Generated at 2026-10-21T04:17:43.730295255+00:00. Canonical report: https://octocounts.com/github/deepseek-ai/DeepGEMM

## Reproduce this report

[Reproduce this exact report and configuration](https://octocounts.com/github/deepseek-ai/DeepGEMM/commit/5081f8513af57e61696de4f4f04b0e707ffb503e?analysis=%7B%22ignoredDirs%22%3A%5B%5D%2C%22ignoredLanguages%22%3A%5B%5D%2C%22profile%22%3A%22default%22%2C%22includeDocs%22%3Afalse%2C%22includeTests%22%3Afalse%2C%22includeGenerated%22%3Afalse%7D&reportId=2b29761e8afec5b008e3eb807d78f85026d8e5d7e9ecb2bce51f370e4fb666f3).

## Report FAQ

### How many lines of code does deepseek-ai/DeepGEMM have?

deepseek-ai/DeepGEMM has 13,756 total lines, including 10,951 code lines, 1,053 comment lines, and 1,752 blank lines.

### How was the deepseek-ai/DeepGEMM line count measured?

OctoCounts resolved the public GitHub repository to commit 5081f8513af5, downloaded the source archive, counted it with tokei, and cached the report by commit, tokei version, and analysis options.

### What commit was counted for deepseek-ai/DeepGEMM?

This OctoCounts report was generated from main at commit 5081f8513af5 on 2026-10-21T04:17:43.730295255+00:00.

## Similar repository reports

- [deepseek-ai/FlashMLA](https://octocounts.com/github/deepseek-ai/FlashMLA) — C++ Header, 13,698 code lines
- [ProjectPhysX/OpenCL-Wrapper](https://octocounts.com/github/ProjectPhysX/OpenCL-Wrapper) — C++ Header, 16,497 code lines
- [rahulsenna/bittorrent-cpp](https://octocounts.com/github/rahulsenna/bittorrent-cpp) — C++ Header, 18,322 code lines
- [jmaczan/tiny-vllm](https://octocounts.com/github/jmaczan/tiny-vllm) — C++ Header, 19,753 code lines
- [IntelSDM/HuntDMA](https://octocounts.com/github/IntelSDM/HuntDMA) — C++ Header, 27,236 code lines

## Related OctoCounts pages

- [Recently analyzed repositories](https://octocounts.com/recent)
- [Popular SLOC reports](https://octocounts.com/popular)
- [Trending GitHub repositories](https://octocounts.com/trending)
- [Hall of Monoliths](https://octocounts.com/hall-of-monoliths)
- [GitHub SLOC counter guide](https://octocounts.com/docs/github-sloc-counter)
- [Counting methodology](https://octocounts.com/docs/methodology)
- [SLOC and code metrics glossary](https://octocounts.com/docs/glossary)
- [Original research: how filtering changes SLOC counts](https://octocounts.com/research)
- [OctoCounts API docs](https://octocounts.com/docs/api)