| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Original HTTPS Page] |
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.
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuse
The model you need rarely fits where it has to run, and the number you are shown is rarely the one that decides. I work on both: vision and sensing on phones, large models on one GPU, and automated trading after costs and tax.
| 11.6x faster | Compiled text generation in Keras on PyTorch, from 15 fixes merged upstream. How → |
| 10.8 → 15.0 tokens/s | A 181 GiB LLM on one 96 GiB GPU, with my gather kernel and expert cache. How → |
| 70% → 90% | Damaged barcodes read on phones, with models trained on 10M+ synthetic images. How → |
| Under 20 parameters | A phone-drop detector in place of one with millions, at 95% less power and 98% → 96% accuracy. How → |
| 69 of 70 | Capital-and-breadth tiers in which an index fund beat holding Indian stocks directly, after costs and tax. RL Alpha Labs → |
| 100 merged PRs | In 38 open-source projects: Keras, KerasHub, vLLM, pip, pydantic. See them → |
LinkedIn · pctablet505.github.io · Open to roles in ML performance, LLM inference, computer vision and on-device AI.
Trading research for Indian stock markets, judged after real costs and tax, not by the best backtest. This repository is the lab's public website; the trading code is private.
HTML
Porchlamp rankings: 11,000 open-source projects ranked by what happens to a stranger's pull request, not by stars.
HTML
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
Static checks that find flaky pytest tests by their pattern, with rules for JAX, PyTorch and NumPy. Alpha.
Python 1
A systemd control plane, an OpenAI-compatible /v1 gateway and a live dashboard for native vLLM on one Linux GPU workstation.
Python
| Back | FazBrowse Home | New Git URL |