DD-DuDa / BitDecodingLinks
A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
☆47Updated 2 weeks ago
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☆48Updated 2 months ago
- ☆60Updated last month
- Implement Flash Attention using Cute.☆87Updated 6 months ago
- ☆75Updated 5 months ago
- ☆77Updated last month
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆80Updated last month
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆38Updated last week
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆71Updated 10 months ago
- ☆23Updated 2 months ago
- Quantized Attention on GPU☆44Updated 7 months ago
- ☆96Updated 9 months ago
- A lightweight design for computation-communication overlap.☆143Updated this week
- ☆19Updated 8 months ago
- ☆49Updated last month
- Github mirror of trition-lang/triton repo.☆39Updated this week
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆54Updated last week
- ☆34Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆92Updated 3 weeks ago
- LLM Inference with Microscaling Format☆23Updated 7 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆99Updated 3 weeks ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆90Updated 2 weeks ago
- DeeperGEMM: crazy optimized version☆69Updated last month
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆109Updated 11 months ago
- ☆54Updated last year
- ☆19Updated 2 months ago
- ☆39Updated last year
- Artifacts of EVT ASPLOS'24☆26Updated last year
- A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores☆51Updated last year
- ☆147Updated 11 months ago
- A practical way of learning Swizzle☆20Updated 4 months ago