Pinned Loading

1. KVSplit KVSplit Public

   Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache quantization. KVSplit enables 8-bit keys & 4-bit values, reducing memory by 59% with <1% quality…

   Python 356 13

2. AgentGuard AgentGuard Public

   Real-time guardrail that shows token spend & kills runaway LLM/agent loops.

   JavaScript 134 7

3. cccl cccl Public

   Forked from NVIDIA/cccl

   CUDA Core Compute Libraries

   C++

4. NVIDIA/NeMo NVIDIA/NeMo Public

   A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

   Python 15.4k 3k

5. jax-ml/jax jax-ml/jax Public

   Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

   Python 33.1k 3.1k

6. synapz synapz Public

   synapz is a research prototype exploring how large language models can adapt teaching content to different cognitive styles. built over a 48-hour sprint with a strict $50 api budget, this project i…

   Python 2