Harry-Chen / InfMoELinks
Inference framework for MoE layers based on TensorRT with Python binding
☆41Updated 4 years ago
Alternatives and similar repositories for InfMoE
Users that are interested in InfMoE are comparing it to the libraries listed below
Sorting:
- Odysseus: Playground of LLM Sequence Parallelism☆72Updated last year
- A Python library transfers PyTorch tensors between CPU and NVMe☆117Updated 8 months ago
- ☆74Updated 4 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- GPTQ inference TVM kernel☆40Updated last year
- A memory efficient DLRM training solution using ColossalAI☆105Updated 2 years ago
- ☆75Updated 2 months ago
- ☆107Updated 11 months ago
- PSTensor provides a way to hack the memory management of tensors in TensorFlow and PyTorch by defining your own C++ Tensor Class.☆10Updated 3 years ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆111Updated 10 months ago
- Distributed DataLoader For Pytorch Based On Ray☆24Updated 3 years ago
- Fairring (FAIR + Herring) is a plug-in for PyTorch that provides a process group for distributed training that outperforms NCCL at large …☆65Updated 3 years ago
- Training neural networks in TensorFlow 2.0 with 5x less memory☆132Updated 3 years ago
- ☆44Updated this week
- ☆16Updated last week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year
- ☆28Updated 4 years ago
- ☆158Updated last year
- Framework to reduce autotune overhead to zero for well known deployments.☆79Updated last week
- pytorch-profiler☆51Updated 2 years ago
- ☆120Updated last year
- ☆39Updated last year
- ☆11Updated 4 years ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆93Updated last month
- Dynamic Tensor Rematerialization prototype (modified PyTorch) and simulator. Paper: https://arxiv.org/abs/2006.09616☆132Updated 2 years ago
- ☆22Updated last year
- Fast and memory-efficient exact attention☆83Updated this week
- 方便扩展的Cuda算子理解和优化框架,仅用在学习使用☆15Updated last year
- ☆75Updated 4 years ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆95Updated 7 years ago