merrymercy / Awesome-Efficient-LLMLinks
A curated list for Efficient Large Language Models
☆11Updated last year
Alternatives and similar repositories for Awesome-Efficient-LLM
Users that are interested in Awesome-Efficient-LLM are comparing it to the libraries listed below
Sorting:
- ☆20Updated last year
- FractalTensor is a programming framework that introduces a novel approach to organizing data in deep neural networks (DNNs) as a list of …☆32Updated last year
- Debug print operator for cudagraph debugging☆14Updated last year
- ☆21Updated 3 years ago
- An external memory allocator example for PyTorch.☆16Updated 5 months ago
- An Attention Superoptimizer☆22Updated last year
- PyTorch compilation tutorial covering TorchScript, torch.fx, and Slapo☆17Updated 2 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆52Updated 5 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆94Updated 4 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆105Updated 7 months ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆45Updated last week
- ☆38Updated last year
- DeeperGEMM: crazy optimized version☆73Updated 8 months ago
- Accepted to MLSys 2026☆70Updated this week
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆20Updated last year
- GPTQ inference TVM kernel☆41Updated last year
- study of Ampere' Sparse Matmul☆18Updated 5 years ago
- ☆84Updated last year
- ☆27Updated 2 years ago
- Artifacts of EVT ASPLOS'24☆28Updated last year
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆61Updated 10 months ago
- ☆40Updated last year
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆49Updated 10 months ago
- ☆52Updated 8 months ago
- A source-to-source compiler for optimizing CUDA dynamic parallelism by aggregating launches☆15Updated 6 years ago
- ☆65Updated 9 months ago
- TiledLower is a Dataflow Analysis and Codegen Framework written in Rust.☆14Updated last year
- GPU operators for sparse tensor operations☆35Updated last year
- Quantized Attention on GPU☆44Updated last year
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆46Updated 7 months ago