perplexityai / pplx-kernelsLinks
Perplexity GPU Kernels
☆461Updated last month
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☆416Updated 3 months ago
- kernels, of the mega variety☆496Updated 3 months ago
- A low-latency & high-throughput serving engine for LLMs☆416Updated 3 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,125Updated this week
- Zero Bubble Pipeline Parallelism☆427Updated 4 months ago
- Ultra and Unified CCL☆544Updated this week
- A Quirky Assortment of CuTe Kernels☆557Updated this week
- Materials for learning SGLang☆579Updated 3 weeks ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆400Updated this week
- ☆116Updated 8 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆417Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆622Updated this week
- Efficient and easy multi-instance LLM serving☆487Updated 2 weeks ago
- ☆295Updated this week
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆311Updated last week
- Applied AI experiments and examples for PyTorch☆294Updated last month
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆756Updated 6 months ago
- ☆233Updated last year
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆211Updated 2 weeks ago
- Cataloging released Triton kernels.☆257Updated 2 weeks ago
- A lightweight design for computation-communication overlap.☆167Updated last week
- Fast low-bit matmul kernels in Triton☆371Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆691Updated 5 months ago
- Fastest kernels written from scratch☆346Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆891Updated this week
- Allow torch tensor memory to be released and resumed later☆135Updated last week
- LLM KV cache compression made easy☆609Updated last week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆573Updated this week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆223Updated this week
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆221Updated 4 months ago