Pinned Loading

1. vllm-project/vllm vllm-project/vllm Public

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python 29.5k 4.4k

2. neuralmagic/deepsparse neuralmagic/deepsparse Public

   Sparsity-aware deep learning inference runtime for CPUs

   Python 3k 176

3. neuralmagic/sparseml neuralmagic/sparseml Public

   Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

   Python 2.1k 146

4. advos advos Public

   RISC-V OS in Rust with hardware support for SiFive's HiFive1 board

   Rust

5. learned_indexes learned_indexes Public

   Experiments on ideas proposed in Tim Kraska's "The Case for Learned Index Structures"

   Python 3

6. torch_bitmask torch_bitmask Public

   Implementations for fast bitmask compression for weight sparsity in PyTorch

   Python 3