- Cambridge, United Kingdom
-
19:40
(UTC +01:00) - in/sudarshan-sreeram
Lists (2)
Sort Name descending (Z-A)
Starred repositories
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
An extremely fast Python linter and code formatter, written in Rust.
You like pytorch? You like micrograd? You love tinygrad! ❤️
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Carbon Language's main repository: documents, design, implementation, and related tools. (NOTE: Carbon Language is experimental; see README)
Curating Top Open Source Apps for Homelab Enthusiasts
A friendly programming language from the future
Versatile typeface for code, from code.
A library for building applications in a consistent and understandable way, with composition, testing, and ergonomics in mind.
Perseus is Khan Academy's exercise question editor and renderer.
Accessible large language models via k-bit quantization for PyTorch.
Bayesian optimization in PyTorch
AI Edge Quantizer: flexible post training quantization for LiteRT models.
DSPy: The framework for programming—not prompting—language models
Offline, privacy-first grammar checker. Fast, open-source, Rust-powered
Dear ImGui: Bloat-free Graphical User interface for C++ with minimal dependencies
Google Research
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.