tile-ai / AttentionEngineLinks
☆50Updated 5 months ago
Alternatives and similar repositories for AttentionEngine
Users that are interested in AttentionEngine are comparing it to the libraries listed below
Sorting:
- ☆65Updated 5 months ago
- Quantized Attention on GPU☆44Updated 11 months ago
- DeeperGEMM: crazy optimized version☆72Updated 5 months ago
- An experimental communicating attention kernel based on DeepEP.☆34Updated 2 months ago
- ☆39Updated 2 months ago
- ☆120Updated 2 months ago
- ☆101Updated 5 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆84Updated last month
- Debug print operator for cudagraph debugging☆14Updated last year
- ☆31Updated 3 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆46Updated 3 months ago
- ☆53Updated last week
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆121Updated 5 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆45Updated 4 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆50Updated last year
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆100Updated 3 months ago
- Implement Flash Attention using Cute.☆96Updated 10 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆119Updated 3 weeks ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 6 months ago
- ☆82Updated 9 months ago
- ☆130Updated 4 months ago
- Estimate MFU for DeepSeekV3☆26Updated 9 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆125Updated 4 months ago
- ☆19Updated last year
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆60Updated 2 weeks ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆147Updated last week
- ☆33Updated 2 weeks ago
- GPTQ inference TVM kernel☆39Updated last year
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆75Updated 4 months ago