MLSysU / TD-PipeLinks
A Throughput-Optimized Pipeline Parallel Inference System for Large Language Models
☆35Updated 3 weeks ago
Alternatives and similar repositories for TD-Pipe
Users that are interested in TD-Pipe are comparing it to the libraries listed below
Sorting:
- ☆117Updated last month
- ☆31Updated last year
- ☆42Updated last year
- GoPTX: Fine-grained GPU Kernel Fusion by PTX-level Instruction Flow Weaving☆18Updated 3 weeks ago
- ☆135Updated 3 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆372Updated 11 months ago
- ☆130Updated 8 months ago
- ☆150Updated 8 months ago
- Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM☆62Updated 2 weeks ago
- Examples of CUDA implementations by Cutlass CuTe☆219Updated last month
- ☆10Updated 3 years ago
- A lightweight design for computation-communication overlap.☆157Updated last week
- ☆81Updated 2 years ago
- Development repository for the Triton-Linalg conversion☆193Updated 6 months ago
- A baseline repository of Auto-Parallelism in Training Neural Networks☆144Updated 3 years ago
- ☆35Updated last year
- ☆28Updated last year
- ☆13Updated last year
- An Optimizing Compiler for Recommendation Model Inference☆25Updated 2 months ago
- This repository is established to store personal notes and annotated papers during daily research.☆142Updated 2 weeks ago
- Github mirror of trition-lang/triton repo.☆52Updated this week
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆151Updated last year
- Yinghan's Code Sample☆344Updated 3 years ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆89Updated 2 years ago
- A Row Decomposition-based Approach for Sparse Matrix Multiplication on GPUs☆22Updated last year
- DeepSeek-V3/R1 inference performance simulator☆165Updated 4 months ago
- 📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).☆39Updated 4 months ago
- High performance Transformer implementation in C++.☆129Updated 7 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆266Updated 5 months ago
- ☆100Updated 3 months ago