Stars
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
DFlash: Block Diffusion for Flash Speculative Decoding
Completely reworked and improved C++ version of Advanced Locomotion System V4.
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Instructed LLM programmer/assistant for Emacs
llama3 implementation one matrix multiplication at a time
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
Construct & orchestrate stand-alone Clojure core.async pipelines with ease or use it to encapsulate & manage complex 'flows' within your application
Tooling to build LLM applications: prompt templating and composition, agents, LLM memory, and other instruments for builders of AI applications.
GPT model token counter, with extra support for OpenAI's completion API
Run LLMs locally. A clojure wrapper for llama.cpp.
Clojure dialect for Flutter and Dart
ReAct agent with access to Python REPL to execute simple workflows. Uses OpenAI GPT-family as language model.
Procedural 3D graphics editor for the web
A library for storing and querying graph data in Clojure
Dockerless Clojure Image builds using deps.edn
Papers from the computer science community to read and discuss.
Interface with complex data via graph mapping.
Library for multiscale visualization of high-resolution multiplexed bioimaging data on the web. Directly renders Zarr and OME-TIFF.
Create evolving artistic images with hot-code-reloaded Lisp and GLSL.