perplexityai / pplx-kernelsLinks
Perplexity GPU Kernels
☆554Updated 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☆457Updated 7 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆459Updated 3 weeks ago
- torchcomms: a modern PyTorch communications API☆321Updated this week
- A Quirky Assortment of CuTe Kernels☆761Updated last week
- Distributed Compiler based on Triton for Parallel Systems☆1,322Updated last month
- Accelerating MoE with IO and Tile-aware Optimizations☆553Updated last week
- Allow torch tensor memory to be released and resumed later☆207Updated 2 weeks ago
- A low-latency & high-throughput serving engine for LLMs☆470Updated 2 weeks ago
- Materials for learning SGLang☆725Updated 3 weeks ago
- kernels, of the mega variety☆652Updated 3 months ago
- ☆340Updated 3 weeks ago
- NVIDIA Inference Xfer Library (NIXL)☆844Updated this week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆252Updated this week
- ☆158Updated last year
- Zero Bubble Pipeline Parallelism☆448Updated 8 months ago
- Applied AI experiments and examples for PyTorch☆314Updated 5 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆639Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆455Updated this week
- Efficient and easy multi-instance LLM serving☆521Updated 4 months ago
- Fastest kernels written from scratch☆524Updated 4 months ago
- A lightweight design for computation-communication overlap.☆213Updated last week
- Perplexity open source garden for inference technology☆340Updated last month
- Helpful kernel tutorials and examples for tile-based GPU programming☆592Updated this week
- ☆273Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆940Updated 2 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆768Updated 9 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆312Updated this week
- Fast low-bit matmul kernels in Triton☆423Updated last month
- AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming☆164Updated this week
- ☆258Updated last year