Preloader

Laya (OS Jev) on Mac M4 CoreML Offline (45 decisions per second)

News Technology
by admin -
0

Instantly share code, notes, and snippets.

@fordnox

fordnox/laya.sh

Last active
September 20, 2026 20:10

Show Gist options

  • Select an option

    Learn more about clone URLs

  • Save fordnox/e592d0f68b543fd044be8e6d040863a0 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs

Save fordnox/e592d0f68b543fd044be8e6d040863a0 to your computer and use it in GitHub Desktop.

Download ZIP
Laya on Mac m4 CoreML Offline https://github.com/mizorewww/laya-coreml

Raw




laya.sh


This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters

Show hidden characters

mkdir test-laya
cd test-laya
uv init
uv add ‘laya-coreml[demo]‘
hf download aac6fef/laya-multilingual-coreml-ane –local-dir models/snake
uv run laya-coreml-snake –model models/snake

@fordnox


fordnox

commented

Sep 20, 2026


•


edited

Loading

Copy link

Copy Markdown



Author

testing https://github.com/mizorewww/laya-coreml

LAYA-CORE-ML.mov


Screenshot 2026-09-20 at 19 02 52

Memory usage

Analysis of sampling python (pid 26208) every 1 millisecond
Process:         python3.12 [26208]
Path:            /Users/USER/*/python3.12
Load Address:    0x10017c000
Identifier:      python3.12
Version:         ???
Code Type:       ARM64
Platform:        macOS
Parent Process:  uv [26207]
Target Type:     live task (Roots Present)

Date/Time:       2026-09-20 23:05:12.300 +0300
Launch Time:     2026-09-20 23:03:49.632 +0300
OS Version:      macOS 27.0 (26A428)
Report Version:  7
Analysis Tool:   /usr/bin/sample

Physical footprint:         560.4M
Physical footprint (peak):  778.0M
Idle exit:                  untracked

<!– –>

@coezbek


coezbek

commented

Sep 20, 2026

Copy link

Copy Markdown


Nice! I just wanted to see what Laya does and put it behind Cloudflare’s typesafe/jev API:

curl https://laya.inference.zaitlabs.com/ai/run 
  -H "Content-Type: application/json" 
  -d '{
    "state": "Help! My payouts have been failing for 3 days.",
    "questions": {
      "is_urgent": {"type": "noul", "instructions": "Does this convey urgency?"}
    }
  }'
{"answers":{"is_urgent":{"type":"noul","noul":0.7894}}}

https://laya.inference.zaitlabs.com/terms

<!– –>

Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment

Source: Hacker News

Choose your Reaction!
Leave a Comment
Related Articles
News Technology
South Korea says AI agents appear to have been used to hack the country's banks

South Korean authorities announced that a series of recent cyber intrusions into the nation’s banking sector were carried out with the help of advanced artificial‑intelligence agents. The attacks, which began in early March, targeted three major banks, compromising customer accounts and siphoning small amounts of funds before the breaches were detected. Investigators say the AI systems were used to automate the reconnaissance phase, identify vulnerable points in the banks’ networks, and deploy malware that could adapt to defensive measures in real time.nnThe technical analysis revealed that the attackers employed machine‑learning algorithms to generate highly realistic phishing emails, increasing the success rate of credential theft. Once inside, the AI‑driven malware scanned for transaction authorization codes and exploited zero‑day vulnerabilities in the banks’ core banking software. The rapid, self‑learning nature of the attacks allowed the perpetrators to evade traditional security tools and reduce the window of exposure to just a few hours.nnIn response, the Korean Financial Services Commission has launched a joint investigation with the National Police Agency and the Cyber Security Center. The agencies are reviewing the banks’ incident‑response protocols, strengthening multi‑

by admin -
50
0