xxyux / SpInferLinks
SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
☆55Updated 5 months ago
Alternatives and similar repositories for SpInfer
Users that are interested in SpInfer are comparing it to the libraries listed below
Sorting:
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆57Updated 3 weeks ago
- ☆63Updated 4 months ago
- Implement Flash Attention using Cute.☆95Updated 8 months ago
- ☆81Updated 7 months ago
- Tile-based language built for AI computation across all scales☆47Updated this week
- ☆150Updated last year
- ☆19Updated 11 months ago
- ☆28Updated 4 months ago
- ☆54Updated last year
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆43Updated 8 months ago
- ☆51Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆74Updated last year
- A lightweight design for computation-communication overlap.☆160Updated this week
- DeeperGEMM: crazy optimized version☆70Updated 3 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆107Updated 3 months ago
- Debug print operator for cudagraph debugging☆13Updated last year
- ☆100Updated 3 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆68Updated 2 months ago
- ☆23Updated this week
- ☆68Updated last year
- ☆50Updated 3 months ago
- ☆98Updated 11 months ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆24Updated 10 months ago
- Quantized Attention on GPU☆44Updated 9 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆217Updated last year
- ☆40Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆93Updated 3 weeks ago
- A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores☆52Updated last year
- Artifacts of EVT ASPLOS'24☆26Updated last year
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆95Updated 2 months ago