lightseekorg/tokenspeed
TokenSpeed is a speed-of-light LLM inference engine.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
TokenSpeed is a speed-of-light LLM inference engine designed for agentic workloads, with TensorRT-LLM-level performance and vLLM-level usability. The goal is to be the most performant inference engine for production agentic workloads. Core components: lifecycle, KV cache ownership, and overlap timing are encoded as a finite-state machine, with safe KV resource reuse enforced by the type system at compile time. a centralized registry including one of the fastest MLA (Multi-head Latent Attention) implementations on Blackwell for agentic workloads. wire, with no Python on the request path. TokenSpeed takes a fundamentally different architectural approach from existing LLM inference engines. The PyTorch Foundation highlighted these architectural differentiators when welcoming TokenSpeed to the PyTorch Ecosystem Landscape: More importantly, TokenSpeed is…
Read the full README ↗ · Preview checked 2026-10-30T14:36:53.378Z
Inside the original README — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
TokenSpeed is a speed-of-light LLM inference engine.
Repository facts
- Owner
- lightseekorg
- Primary language
- Python
- Stars
- 2,290
- Forks
- 331
- Open issues + pull requests
- 81
- License
- MIT
- Archived
- No
- Default branch
- main
- Created
- 2026-05-06T13:13:21.000Z
- Last push
- 2026-10-15T10:22:52.000Z
Topics and intended use
Owner-supplied topics: b200, b300, blackwell, deepseek, gb200, gb300, glm, gpt-oss, inkling, kimi, lightseek, llm, mi355x, mi455x, minimax, qwen, rubin, speed-of-light, tokenspeed, vlm
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-15T12:06:21.745Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer