feifeibear / ChituAttentionLinks
Quantized Attention on GPU
☆44Updated 8 months ago
Alternatives and similar repositories for ChituAttention
Users that are interested in ChituAttention are comparing it to the libraries listed below
Sorting:
- ☆50Updated 2 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆42Updated last month
- ☆75Updated 2 months ago
- ☆60Updated 3 months ago
- ☆79Updated 6 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆46Updated last year
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆31Updated 8 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
- Odysseus: Playground of LLM Sequence Parallelism☆72Updated last year
- Framework to reduce autotune overhead to zero for well known deployments.☆79Updated last week
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆50Updated 4 months ago
- DeeperGEMM: crazy optimized version☆71Updated 3 months ago
- ☆44Updated this week
- Debug print operator for cudagraph debugging☆13Updated last year
- Implement Flash Attention using Cute.☆92Updated 7 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆93Updated last month
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆31Updated 2 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆124Updated 2 months ago
- GPTQ inference TVM kernel☆40Updated last year
- ☆19Updated 7 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆17Updated last month
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆64Updated last month
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆57Updated 3 weeks ago
- 16-fold memory access reduction with nearly no loss☆103Updated 4 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆93Updated 2 months ago
- ☆123Updated 2 months ago
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆18Updated 5 months ago
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆61Updated last week
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆56Updated last week
- An experimental communicating attention kernel based on DeepEP.☆32Updated last week