tiktoken 是一种快速的 BPE 标记器，可与 OpenAI 的模型一起使用。
Python · active 2025-03-30 → 2026-07-18 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 476 days from 2025-03-30 to 2026-07-18. Pushes: 13 total, peak 3 in a day. Pull requests: 32 total, peak 3 in a day. Issues: 51 total, peak 8 in a day. Comments: 92 total, peak 5 in a day. Stars: 1,819 total, peak 25 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| hauntsaninja | 54 | 12 | 9 | 16 |
| swamy18 | 8 | 0 | 0 | 0 |
| ngoldbaum | 6 | 0 | 2 | 4 |
| 213771507034 | 4 | 0 | 0 | 0 |
| TaylorN15 | 4 | 0 | 1 | 3 |
| reneleonhardt | 4 | 0 | 1 | 2 |
| devatsecure | 4 | 0 | 0 | 2 |
| the01338 | 3 | 0 | 0 | 3 |
| tarekgh | 3 | 0 | 0 | 1 |
| rjarun8235 | 3 | 0 | 0 | 3 |
| ColemanDunn | 2 | 0 | 0 | 2 |
| eshaanpathak | 2 | 0 | 0 | 1 |
| yangchou19 | 2 | 0 | 0 | 1 |
| fast-blender-add-ons-dot-com | 2 | 0 | 0 | 2 |
| EricAveritt | 2 | 0 | 0 | 2 |
| Majdoddin | 2 | 0 | 0 | 1 |
| eliliam | 2 | 0 | 1 | 1 |
| Fool256 | 2 | 0 | 0 | 0 |
| dtrifiro | 2 | 0 | 1 | 1 |
| kmk142789 | 2 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#572leandro4979-hub2026-06-21 22:48
- Pull request#565enlorik2026-06-06 11:40
- Pull request#562AvinZarlez2026-05-27 22:55
- Issue comment#52111953430152026-05-25 05:19tiktoken 0.12 cannot handle qwen3.5 in huggingface
- Pull request#556LeSingh12026-05-24 10:14
- Issue comment#458fallintoplace2026-05-24 10:10fix: remove conflicting <|reserved_200018|>; add token-id uniqueness …
- Issue#534hauntsaninja2026-05-24 08:43build_sdist uploads artifact with empty name (matrix variables undefined)
- Pull request#535MukundaKatta2026-05-24 08:43
- Issue comment#15jbbqqf2026-05-23 10:09Extremely Long Text results in PanicException, which is hard to catch in python code
- Pull request#537HrushiYadav2026-04-30 06:07
- Issue#534gounthar2026-04-26 12:45build_sdist uploads artifact with empty name (matrix variables undefined)
- Issue comment#532Marven112026-04-25 19:12The encode algorithm can be O(n) instead of O(nlog(n))
- Issue#519impacterai2026-04-03 23:06Add Repurpose AI — AI content repurposing tool
- Issue comment#509joaquinhuigomez2026-03-29 02:54Add PyInstaller hooks for tiktoken
- Issue#512gingangelmaster-Grand2026-03-22 19:50https://tiktok.com/@grandmasterangel1111
- Issue comment#511nicezic2026-03-22 05:36[RFC] Korean Tokenization: Jamo Decomposition as Pre-tokenizer (A Blueprint for Compositional Scripts)
- Pull request#507eeea22222026-03-14 00:50
- Pull request#495hauntsaninja2026-02-08 20:53
- Issue#492hauntsaninja2026-02-08 07:13[CODE CONTRIBUTION] Add memory usage profiler
- Issue#493hauntsaninja2026-02-08 07:13[CODE CONTRIBUTION] Add encoding statistics tracker
- Issue#494hauntsaninja2026-02-08 07:13[CODE CONTRIBUTION] Add lazy encoding loader
- Issue#479hauntsaninja2026-02-08 07:12Add benchmarking suite for BPE tokenization performance
- Issue#494swamy182026-02-07 14:20[CODE CONTRIBUTION] Add lazy encoding loader
- Issue#488swamy182026-02-07 14:14[CODE CONTRIBUTION] Add adaptive batch size optimizer
- Issue#486swamy182026-02-07 14:01Add comprehensive wheel support for ARM64 architectures
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,819 stars here means stars gained during the window, not the repo's star count.