xxyux / SpInfer
SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
☆32Updated last week
Alternatives and similar repositories for SpInfer:
Users that are interested in SpInfer are comparing it to the libraries listed below
- ☆19Updated 6 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆25Updated last week
- ☆29Updated 11 months ago
- Tutorials of Extending and importing TVM with CMAKE Include dependency.☆13Updated 5 months ago
- ☆50Updated 2 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆63Updated last week
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆60Updated 7 months ago
- Artifacts of EVT ASPLOS'24☆23Updated last year
- study of Ampere' Sparse Matmul☆17Updated 4 years ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆90Updated last month
- Optimize GEMM with tensorcore step by step☆24Updated last year
- Implement Flash Attention using Cute.☆74Updated 3 months ago
- llama INT4 cuda inference with AWQ☆53Updated 2 months ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆59Updated 6 months ago
- play gemm with tvm☆89Updated last year
- Quantized Attention on GPU☆45Updated 4 months ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆17Updated 6 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆108Updated 6 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆35Updated 3 weeks ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆49Updated 10 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆74Updated this week
- ThrillerFlow is a Dataflow Analysis and Codegen Framework written in Rust.☆14Updated 4 months ago
- GPTQ inference TVM kernel☆38Updated 11 months ago
- ☆10Updated 3 weeks ago
- ☆67Updated 2 months ago
- ☆39Updated 5 years ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆85Updated 2 years ago
- ☆91Updated 6 months ago
- An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.☆51Updated 8 months ago
- GPU TopK Benchmark☆14Updated 3 months ago