DD-DuDa / BitDecodingLinks
A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
☆56Updated last week
Alternatives and similar repositories for BitDecoding
Users that are interested in BitDecoding are comparing it to the libraries listed below
Sorting:
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆50Updated 4 months ago
- Implement Flash Attention using Cute.☆92Updated 7 months ago
- ☆60Updated 3 months ago
- ☆89Updated 2 months ago
- A lightweight design for computation-communication overlap.☆154Updated last month
- ☆25Updated 4 months ago
- ☆79Updated 6 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆57Updated 2 weeks ago
- ☆96Updated 10 months ago
- ☆150Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆93Updated 2 months ago
- 使用 cutlass 仓 库在 ada 架构上实现 fp8 的 flash attention☆74Updated 11 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆64Updated last month
- DeeperGEMM: crazy optimized version☆71Updated 2 months ago
- ☆37Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆106Updated 2 months ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆63Updated 10 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆183Updated 6 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆91Updated last month
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆216Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated 3 weeks ago
- Tile-based language built for AI computation across all scales☆30Updated last week
- ☆49Updated 2 months ago
- A practical way of learning Swizzle☆22Updated 6 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆40Updated last month
- Examples of CUDA implementations by Cutlass CuTe☆214Updated last month
- High performance Transformer implementation in C++.☆128Updated 6 months ago
- Optimize GEMM with tensorcore step by step☆31Updated last year
- ☆78Updated 3 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year