Skip to content
View pctablet505's full-sized avatar
9 followers · 1 following

Achievements

Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Pull Sharkx3Achievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Pull Sharkx3Achievement: Quickdraw

Block or report pctablet505

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pctablet505/README.md
Big models, small places, real numbers. pctablet505.

ON-DEVICE AI

<22 parameters

replaced a deep-learning drop detector with millions, on over 95% less power

LLM INFERENCE

181 GiB model

on one 96 GiB GPU, decoding 15.0 tokens a second

KERAS · ON-DEVICE AI

1 call to a phone

model.export(..., format="litert")
Before: separate tooling, and no path from PyTorch

KERAS ON PYTORCH

11.6× faster

compiled text generation, from fixes merged upstream

VISION · BIOMETRICS

87 ms

to find one face among 10,000+ people, down from 1,200 ms

OPEN SOURCE

100+ merged PRs

Keras KerasHub vLLM pip poetry pydantic pyright typeshed trio

PORCHLAMP.ORG

Will they merge your PR?

See which open-source projects reply to, review and merge a stranger's pull request

RLALPHALABS.COM

Does it beat an index fund?

Automated trading on Indian stocks: a survivorship-free simulator and RL agents in JAX, judged after costs and tax

Pinned Loading

  1. glm53-flash-single-gpu glm53-flash-single-gpu Public

    GLM-5.3-Flash, a 181 GiB mixture-of-experts model, served from one 96 GiB GPU: a gather kernel and a cache of the busiest experts took decoding from 10.8 to 15.0 tokens/s as shipped. Measurements a…

    Python 1

  2. porchlamp porchlamp Public

    Porchlamp rankings: 11,000 open-source projects ranked by what happens to a stranger's pull request, not by stars.

    HTML

  3. flakehound flakehound Public

    Static checks that find flaky pytest tests by their pattern, with rules for JAX, PyTorch and NumPy. Alpha.

    Python 1

  4. servedeck servedeck Public

    A systemd control plane, an OpenAI-compatible /v1 gateway and a live dashboard for native vLLM on one Linux GPU workstation.

    Python

  5. RLAlphaLabs RLAlphaLabs Public

    A survivorship-free simulator and RL agents in JAX for automated trading on Indian stocks, judged against an index fund after real costs and tax. This repository is the lab's website; the trading c…

    HTML

  6. ML-Guide ML-Guide Public

    The AI and ML courses I would take, in order: four stages from curious to doing machine learning work, with what each one gives you.

    3 3