lightseekorg/tokenspeed

tokenspeed

✅ Recently maintained

TokenSpeed is a speed-of-light LLM inference engine.

2,850Stars
390Forks
+437-day stars

Python · MIT · Last push 2026-11-03

Official repository & installation ↗
deepseekgpt-osskimilightseekllmminimaxqwenspeed-of-lighttokenspeedblackwell

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2026-05-042026-11-03
View historical data
DateStars
2026-10-052,187
2026-10-062,188
2026-10-072,195
2026-10-082,200
2026-10-092,203
2026-10-102,206
2026-10-112,208
2026-10-122,211
2026-10-132,227
2026-10-142,258
2026-10-152,569
2026-10-162,669
2026-10-172,690
2026-10-182,699
2026-10-192,714
2026-10-202,729
2026-10-212,740
2026-10-222,764
2026-10-232,771
2026-10-242,775
2026-10-252,786
2026-10-262,804
2026-10-272,813
2026-10-282,820
2026-10-292,824
2026-10-302,829
2026-10-312,832
2026-11-012,843
2026-11-022,850
2026-11-032,850

Get the project

git clone https://github.com/lightseekorg/tokenspeed.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

★ 38,386ollama

Run DeepSeek, Qwen, Gemma and other LLMs locally with one command, plus model management and an API.

★ 185,745openinterpreter

A coding agent for open models like Kimi K3 and GLM 5.3

★ 68,783