NandhaKishorM/laya

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

Multilingual, non-autoregressive System 1 decision engine. Typed decisions over 100+ languages in a single forward pass — 33 ms — trained with reinforcement learning against strictly proper scoring rules (RLCD), with a router that picks the right checkpoint per request. [](https://colab.research.google.com/drive/15d4YvKHeHjshVb-6PRTfqVllxih2S3?usp=sharing) [](https://pypi.org/project/laya/) [](https://nandhakishorm.github.io/laya/) [](https://huggingface.co/convaiinnovations/laya) [](https://huggingface.co/convaiinnovations/laya-multilingual) [](https://huggingface.co/spaces/convaiinnovations/laya-demo) [](https://dev.to/nandakishorm6cc0adfde9f/i-built-non-autoregressive-decision-models-a-year-ago-then-a-frontier-lab-called-it-a-18me) [](https://www.buymeacoffee.com/nandakishorm) [](https://opensource.org/licenses/Apache-2.0) With uv, run uv add laya in a uv project or uv pip install laya in a virtual environment. Python 3.10 or newer. Optional extras: laya[serve] (HTTP server), laya[mcp] (MCP server), laya[langchain] (LangChain and LangGraph), laya[llamaindex] (LlamaIndex selectors), laya[crewai] (CrewAI routing), laya[onnx] (ONNX Runtime), laya[fast] (TileLang GPU fast path), laya[structured] (pydantic models in decide). Step-by-step setup for each platform, CPU-only or GPU PyTorch builds, and troubleshooting are in Installation details. For TypeScript / Node.js / browser, see laya-ts/. npm releases (npm install laya-ts) are published from this repository's laya-ts-v release tags. Long documents. laya-multilingual reads up to 8,192 tokens with maxlen=8192.…

NandhaKishorM/laya on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-11-03T06:54:22.129Z

Inside the original README — Document outline
  1. Installation
  2. Quickstart
  3. Fine-tune for better accuracy
  4. Documentation
  5. What's new in 0.4.21
  6. Where to go next
  7. Installation details
  8. Command line
  9. macOS, including Intel Macs
  10. Running from this checkout
  11. Try it locally: web GUI + JSON API
  12. Python HTTP client

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: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

Repository facts

Owner
NandhaKishorM
Primary language
Python
Stars
33,306
Forks
2,989
Open issues + pull requests
83
License
Apache-2.0
Archived
No
Default branch
main
Created
2026-09-18T04:46:33.000Z
Last push
2026-10-17T16:58:09.000Z

Topics and intended use

Owner-supplied topics: calibration, classification, decision-model, huggingface, jev, modernbert, multilingual, nlp, python, pytorch, routing, typed-decisions, zero-shot

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.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-10-18T12:11:03.329Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

public-apis/public-apis

EbookFoundation/free-programming-books

donnemartin/system-design-primer

vinta/awesome-python

practical-tutorials/project-based-learning

NousResearch/hermes-agent