DD-DuDa / BitDecodingLinks
A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
☆60Updated last month
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☆58Updated 6 months ago
- Implement Flash Attention using Cute.☆95Updated 9 months ago
- ☆64Updated 5 months ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆130Updated 2 weeks ago
- ☆106Updated 4 months ago
- A lightweight design for computation-communication overlap.☆177Updated 2 weeks ago
- ☆28Updated 6 months ago
- ☆98Updated last year
- ☆82Updated 8 months ago
- Tile-based language built for AI computation across all scales☆61Updated this week
- ☆43Updated last year
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆72Updated 3 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆221Updated 2 years ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆41Updated last week
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆75Updated last year
- High performance Transformer implementation in C++.☆134Updated 8 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆99Updated 3 weeks ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆66Updated this week
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆186Updated 8 months ago
- ☆151Updated last year
- DeeperGEMM: crazy optimized version☆71Updated 4 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆118Updated 4 months ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆24Updated 11 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆44Updated 3 months ago
- ☆30Updated 3 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆61Updated 2 weeks ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆67Updated last year
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆97Updated 3 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated 2 weeks ago
- PyTorch bindings for CUTLASS grouped GEMM.☆123Updated 4 months ago