perplexityai / pplx-kernelsLinks
Perplexity GPU Kernels
☆529Updated 2 weeks 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☆436Updated 5 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,241Updated this week
- A low-latency & high-throughput serving engine for LLMs☆445Updated last month
- NVIDIA Inference Xfer Library (NIXL)☆721Updated this week
- A Quirky Assortment of CuTe Kernels☆660Updated 3 weeks ago
- ☆316Updated last week
- Zero Bubble Pipeline Parallelism☆435Updated 6 months ago
- kernels, of the mega variety☆608Updated last month
- torchcomms: a modern PyTorch communications API☆291Updated this week
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆385Updated last week
- Materials for learning SGLang☆650Updated this week
- ☆148Updated 10 months ago
- Efficient and easy multi-instance LLM serving☆510Updated 2 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆230Updated last week
- Applied AI experiments and examples for PyTorch☆305Updated 3 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆483Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆437Updated this week
- Fast low-bit matmul kernels in Triton☆398Updated this week
- Allow torch tensor memory to be released and resumed later☆167Updated last week
- Perplexity open source garden for inference technology☆232Updated this week
- Fastest kernels written from scratch☆394Updated 2 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆729Updated 7 months ago
- ☆244Updated last year
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA (+ more DSLs)☆663Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆781Updated 8 months ago
- Cataloging released Triton kernels.☆267Updated 2 months ago
- LLM KV cache compression made easy☆688Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆915Updated 3 weeks ago
- A lightweight design for computation-communication overlap.☆187Updated last month
- ☆250Updated this week