perplexityai / pplx-kernelsLinks
Perplexity GPU Kernels
☆425Updated this week
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☆405Updated 2 months ago
- Distributed Compiler based on Triton for Parallel Systems☆941Updated last week
- A low-latency & high-throughput serving engine for LLMs☆402Updated 2 months ago
- kernels, of the mega variety☆466Updated 2 months ago
- Zero Bubble Pipeline Parallelism☆415Updated 3 months ago
- A Quirky Assortment of CuTe Kernels☆388Updated this week
- Ultra and Unified CCL☆468Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆523Updated this week
- Applied AI experiments and examples for PyTorch☆289Updated 2 months ago
- Materials for learning SGLang☆522Updated 3 weeks ago
- A lightweight design for computation-communication overlap.☆155Updated last month
- ☆106Updated 7 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆731Updated 5 months ago
- Efficient and easy multi-instance LLM serving☆458Updated this week
- ☆228Updated last year
- Fast low-bit matmul kernels in Triton☆339Updated last week
- Fastest kernels written from scratch☆310Updated 4 months ago
- ☆250Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆394Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆659Updated 4 months ago
- High performance Transformer implementation in C++.☆129Updated 6 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆264Updated 5 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆281Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆862Updated last month
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆185Updated this week
- ☆227Updated last week
- LLM KV cache compression made easy☆570Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆656Updated this week
- Allow torch tensor memory to be released and resumed later☆96Updated last month
- Cataloging released Triton kernels.☆251Updated 7 months ago