Skip to main content
Back to trending

tokenspeed

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

  • b200
  • b300
  • blackwell
  • deepseek
  • gb200
  • gb300
  • glm
  • gpt-oss
  • inkling
  • kimi
  • lightseek
  • llm
  • mi355x
  • mi455x
  • minimax
  • qwen
  • rubin
  • speed-of-light
  • tokenspeed
  • vlm
View on GitHub
Stars
2,671
Forks
352
+ today
+4
Created
5mo

Ranking data as of October 16, 2026 (UTC).

Star History

Today, hour by hour

2,671 stars
04

Overview

TokenSpeed is a speed-of-light LLM inference engine. It ranks #109 on GitTiger, gaining +4 stars on October 16, 2026 (UTC).

The project is written in Python and has 352 forks. It was created 5mo ago.

Installation
git clone https://github.com/lightseekorg/tokenspeed.git
cd tokenspeed
# see README for setup