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:
- FractalTensor is a programming framework that introduces a novel approach to organizing data in deep neural networks (DNNs) as a list of …☆25Updated 5 months ago
- ☆19Updated 8 months ago
- An Attention Superoptimizer☆21Updated 4 months ago
- PyTorch compilation tutorial covering TorchScript, torch.fx, and Slapo☆18Updated 2 years ago
- ☆32Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated last month
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆25Updated 3 months ago
- TensorRT LLM Benchmark Configuration☆13Updated 10 months ago
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆18Updated last week
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- GPU operators for sparse tensor operations☆32Updated last year
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆51Updated 2 weeks ago
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆29Updated 6 months ago
- ☆14Updated last year
- An external memory allocator example for PyTorch.☆14Updated 3 years ago
- DeeperGEMM: crazy optimized version☆69Updated last month
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆47Updated 2 months ago
- GPTQ inference TVM kernel☆40Updated last year
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆36Updated last month
- SparseTIR: Sparse Tensor Compiler for Deep Learning☆138Updated 2 years ago
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆20Updated last year
- ☆59Updated last month
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆15Updated 3 weeks ago
- ☆70Updated 3 years ago
- ☆49Updated 2 weeks ago
- 方便扩展的Cuda算子理解和优化框架,仅用在学习使用☆15Updated 11 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆88Updated this week
- Memory Optimizations for Deep Learning (ICML 2023)☆64Updated last year
- Framework to reduce autotune overhead to zero for well known deployments.☆74Updated 3 weeks ago
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆38Updated 2 years ago