perplexityai / pplx-kernelsLinks
Perplexity GPU Kernels
☆548Updated 2 months ago
Alternatives and similar repositories for pplx-kernels
Users that are interested in pplx-kernels are comparing it to the libraries listed below
Sorting:
- Dynamic Memory Management for Serving LLMs without PagedAttention☆453Updated 7 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,303Updated last week
- A low-latency & high-throughput serving engine for LLMs☆462Updated 2 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆433Updated this week
- A Quirky Assortment of CuTe Kernels☆732Updated this week
- Materials for learning SGLang☆709Updated 3 weeks ago
- torchcomms: a modern PyTorch communications API☆315Updated this week
- kernels, of the mega variety☆637Updated 3 months ago
- Efficient and easy multi-instance LLM serving☆519Updated 4 months ago
- Allow torch tensor memory to be released and resumed later☆196Updated last month
- NVIDIA Inference Xfer Library (NIXL)☆788Updated this week
- ☆337Updated this week
- Zero Bubble Pipeline Parallelism☆444Updated 8 months ago
- Applied AI experiments and examples for PyTorch☆312Updated 4 months ago
- ☆153Updated last year
- Accelerating MoE with IO and Tile-aware Optimizations☆500Updated last week
- Fastest kernels written from scratch☆507Updated 3 months ago
- Fast low-bit matmul kernels in Triton☆416Updated 2 weeks ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆449Updated this week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆308Updated last week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆597Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆758Updated 9 months ago
- ☆254Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆799Updated 10 months ago
- Perplexity open source garden for inference technology☆321Updated last week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆250Updated 3 weeks ago
- A throughput-oriented high-performance serving framework for LLMs☆929Updated 2 months ago
- ☆269Updated last week
- A lightweight design for computation-communication overlap.☆207Updated last week
- Cataloging released Triton kernels.☆282Updated 3 months ago