feifeibear / ChituAttention
Quantized Attention on GPU
☆30Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for ChituAttention
- GPTQ inference TVM kernel☆36Updated 6 months ago
- ☆18Updated last month
- A sparse attention kernel supporting mix sparse patterns☆55Updated last month
- Odysseus: Playground of LLM Sequence Parallelism☆57Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆53Updated 3 weeks ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆52Updated 3 months ago
- ☆79Updated 2 months ago
- Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.☆23Updated 2 weeks ago
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆63Updated last week
- ☆16Updated this week
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆57Updated this week
- ☆35Updated 2 weeks ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆32Updated 3 months ago
- Debug print operator for cudagraph debugging☆10Updated 3 months ago
- ☆64Updated 3 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆26Updated 5 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆98Updated 2 months ago
- Efficient, Flexible and Portable Structured Generation☆40Updated this week
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆85Updated 8 months ago
- ☆42Updated 7 months ago
- 16-fold memory access reduction with nearly no loss☆59Updated last week
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆15Updated this week
- ☆42Updated 6 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated 11 months ago
- TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.☆154Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- ☆46Updated 5 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆90Updated 4 months ago
- llama INT4 cuda inference with AWQ☆48Updated 4 months ago