DD-DuDa / BitLadderLinks
A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
☆61Updated 3 weeks ago
Alternatives and similar repositories for BitLadder
Users that are interested in BitLadder are comparing it to the libraries listed below
Sorting:
- Implement Flash Attention using Cute.☆96Updated 10 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 7 months ago
- ☆34Updated 2 weeks ago
- ☆65Updated 6 months ago
- ☆110Updated 5 months ago
- A lightweight design for computation-communication overlap.☆183Updated last month
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆87Updated 5 months ago
- ☆159Updated last year
- ☆83Updated 9 months ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆142Updated last month
- Multi-Level Triton Runner supporting Python, IR, PTX, and cubin.☆76Updated this week
- Tile-based language built for AI computation across all scales☆78Updated this week
- ☆101Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆78Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆124Updated 6 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆48Updated last month
- ☆47Updated last year
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆45Updated 5 months ago
- ☆55Updated last year
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆24Updated last year
- Optimize GEMM with tensorcore step by step☆32Updated last year
- Examples of CUDA implementations by Cutlass CuTe☆247Updated 4 months ago
- DeeperGEMM: crazy optimized version☆73Updated 6 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆78Updated this week
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆68Updated last year
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆222Updated 2 years ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Updated 2 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆186Updated 9 months ago
- A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores☆54Updated last year
- High performance Transformer implementation in C++.☆141Updated 9 months ago