|
ON-DEVICE AI replaced a deep-learning drop detector with millions, on over 95% less power |
LLM INFERENCE on one 96 GiB GPU, decoding 15.0 tokens a second |
|
KERAS · ON-DEVICE AI
|
KERAS ON PYTORCH compiled text generation, from fixes merged upstream |
|
VISION · BIOMETRICS to find one face among 10,000+ people, down from 1,200 ms |
OPEN SOURCE Keras KerasHub vLLM pip poetry pydantic pyright typeshed trio |
|
PORCHLAMP.ORG See which open-source projects reply to, review and merge a stranger's pull request |
RLALPHALABS.COM Automated trading on Indian stocks: a survivorship-free simulator and RL agents in JAX, judged after costs and tax |
-
Google
- India
-
22:42
(UTC +05:30) - https://pctablet505.github.io/
- in/pctablet505
- https://rlalphalabs.com/
- https://porchlamp.org/
- https://dev.to/pctablet505
Pinned Loading
-
glm53-flash-single-gpu
glm53-flash-single-gpu PublicGLM-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
-
porchlamp
porchlamp PublicFind open source projects to contribute to, ranked by what happens to a stranger's pull request, not by stars.
HTML
-
flakehound
flakehound PublicStatic checks that find flaky pytest tests by their pattern, with rules for JAX, PyTorch and NumPy. Alpha.
Python 1
-
servedeck
servedeck PublicA systemd control plane, an OpenAI-compatible /v1 gateway and a live dashboard for native vLLM on one Linux GPU workstation.
Python
-
RLAlphaLabs
RLAlphaLabs PublicA 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
If the problem persists, check the GitHub status page or contact support.