ai-dynamo / aiconfiguratorLinks
Offline optimization of your disaggregated Dynamo graph
☆45Updated this week
Alternatives and similar repositories for aiconfigurator
Users that are interested in aiconfigurator are comparing it to the libraries listed below
Sorting:
- A lightweight design for computation-communication overlap.☆160Updated last week
- Perplexity GPU Kernels☆449Updated 3 weeks ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆195Updated last week
- Fast and memory-efficient exact attention☆91Updated this week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆214Updated this week
- Ultra and Unified CCL☆511Updated this week
- A Python library transfers PyTorch tensors between CPU and NVMe☆120Updated 9 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆105Updated 3 months ago
- NVIDIA Inference Xfer Library (NIXL)☆569Updated this week
- extensible collectives library in triton☆88Updated 5 months ago
- A low-latency & high-throughput serving engine for LLMs☆408Updated 3 months ago
- ☆88Updated 9 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆407Updated 3 months ago
- Efficient and easy multi-instance LLM serving☆475Updated 2 weeks ago
- ☆234Updated last week
- Applied AI experiments and examples for PyTorch☆292Updated last week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆153Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆404Updated this week
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆79Updated 9 months ago
- DeeperGEMM: crazy optimized version☆70Updated 3 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year
- ☆111Updated 8 months ago
- ☆92Updated 5 months ago
- Cataloging released Triton kernels.☆252Updated 7 months ago
- ☆69Updated last year
- ☆229Updated last year
- Fast low-bit matmul kernels in Triton☆356Updated last week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆261Updated last month
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆95Updated 2 months ago
- ☆84Updated this week