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
☆13Updated 10 months ago
Alternatives and similar repositories for cuda_op_benchmark:
Users that are interested in cuda_op_benchmark are comparing it to the libraries listed below
- Benchmark tests supporting the TiledCUDA library.☆16Updated 4 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆80Updated last week
- GPTQ inference TVM kernel☆38Updated 11 months ago
- ☆39Updated last week
- A practical way of learning Swizzle☆17Updated 2 months ago
- FractalTensor is a programming framework that introduces a novel approach to organizing data in deep neural networks (DNNs) as a list of …☆26Updated 3 months ago
- ☆19Updated 6 months ago
- ☆57Updated last week
- A simple calculation for LLM MFU.☆34Updated last month
- Quantized Attention on GPU☆45Updated 4 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆42Updated 3 weeks ago
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆25Updated 2 months ago
- TensorRT LLM Benchmark Configuration☆13Updated 8 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆36Updated 2 weeks ago
- Framework to reduce autotune overhead to zero for well known deployments.☆63Updated this week
- Implement Flash Attention using Cute.☆74Updated 4 months ago
- Transformers components but in Triton☆32Updated last month
- An Attention Superoptimizer☆21Updated 2 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆108Updated 7 months ago
- ☆26Updated last year
- Inference framework for MoE layers based on TensorRT with Python binding☆41Updated 3 years ago
- TiledKernel is a code generation library based on macro kernels and memory hierarchy graph data structure.☆19Updated 11 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆32Updated 3 weeks ago
- DeeperGEMM: crazy optimized version☆65Updated 2 weeks ago
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆18Updated this week
- Implementation from scratch in C of the Multi-head latent attention used in the Deepseek-v3 technical paper.☆17Updated 3 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆68Updated 2 weeks ago
- ThrillerFlow is a Dataflow Analysis and Codegen Framework written in Rust.☆14Updated 4 months ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆17Updated 6 months ago
- ☆39Updated 10 months ago