SGLang is a high-performance serving framework for large language models and multimodal models.
An open source Valkey client library that supports Valkey, and Redis open source 6.2, 7.0 and 7.2...
Triton with Windows support
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
A lightweight library for xPU kernel JIT compilation
Fast and memory-efficient exact attention
Templating rendering and generation parsing for Cohere models.
PyIceberg
TokenSpeed is a speed-of-light LLM inference engine.
DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers
