Alternatives and similar repositories for ninetoothed

Users that are interested in ninetoothed are comparing it to the libraries listed below

• tsinghua-ideal / Canvas
  Canvas: End-to-End Kernel Architecture Search in Neural Networks
  ☆26Updated 5 months ago
• sjtu-epcc / Tacker
  Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS
  ☆25Updated 3 months ago
• TiledTensor / TiledKernel
  TiledKernel is a code generation library based on macro kernels and memory hierarchy graph data structure.
  ☆19Updated last year
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆155Updated 7 months ago
• TiledTensor / TiledLower
  ThrillerFlow is a Dataflow Analysis and Codegen Framework written in Rust.
  ☆14Updated 5 months ago
• shenh10 / DeepSeek_Simulator
  ☆65Updated last month
• cassiewilliam / cuda_op_benchmark
  方便扩展的Cuda算子理解和优化框架，仅用在学习使用
  ☆15Updated 11 months ago
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆120Updated last month
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆34Updated 3 weeks ago
• microsoft / FractalTensor
  FractalTensor is a programming framework that introduces a novel approach to organizing data in deep neural networks (DNNs) as a list of …
  ☆26Updated 4 months ago
• AlibabaResearch / mononn
  ☆28Updated 10 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆85Updated this week
• flashinfer-ai / cutlass-viz
  ☆58Updated 3 weeks ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆39Updated last week
• TiledTensor / TiledCUDA
  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …
  ☆181Updated 3 months ago
• NEO-MLSys25 / NEO
  NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
  ☆27Updated 2 months ago
• Yongqi-Zhuo / triton-tvm
  Triton to TVM transpiler.
  ☆19Updated 7 months ago
• thunlp / TritonBench
  TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
  ☆38Updated 2 months ago
• hao-ai-lab / MuxServe
  ☆60Updated 11 months ago
• xxyux / SpInfer
  SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
  ☆44Updated last month
• WukLab / preble
  Stateful LLM Serving
  ☆67Updated 2 months ago
• heheda12345 / MagPy
  ☆39Updated 11 months ago
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆95Updated last year
• nox-410 / tvm.tl
  An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.
  ☆50Updated 9 months ago
• alibaba / easydist
  Automated Parallelization System and Infrastructure for Multiple Ecosystems
  ☆78Updated 5 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆113Updated last week
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆73Updated 2 weeks ago
• SJTU-IPADS / disb
  DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.
  ☆52Updated 8 months ago
• InfiniTensor / InfiniLM
  ☆104Updated 2 months ago
• pku-liang / MAGIS
  MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)
  ☆50Updated 11 months ago