torchpipe / torchpipe

An Alternative for Triton Inference Server. Boosting DL Service Throughput 1.5-4x by Ensemble Pipeline Serving with Concurrent CUDA Streams for PyTorch/LibTorch Frontend and TensorRT/CVCUDA, etc., Backends

Date Created 2023-10-24 (7 months ago)

Commits 140 (last one 9 days ago)

Stargazers 130 (1 this week)

Watchers 6 (0 this week)

Forks 12

License apache-2.0

Ranking

RepositoryStats indexes 523,840 repositories, of these torchpipe/torchpipe is ranked #224,638 (57th percentile) for total stargazers, and #282,917 for total watchers. Github reports the primary language for this repository as C++, for repositories using this language it is ranked #12,582/28,144.

torchpipe/torchpipe is also tagged with popular topics, for these it's ranked: pytorch (#2,925/5505), deployment (#235/413)

Other Information

There have been 9 releases, the latest one was published on 2024-05-22 (9 days ago)

Homepage URL: https://torchpipe.github.io/

All Topics

ray serve cvcuda pytorch serving tensorrt inference ray-serve torch2trt deployment pipeline-parallelism triton-inference-server

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

140 commits on the default branch (main) since jan '22

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

The primary language is C++ but there's also others...

updated: 2024-05-28 @ 12:42pm, id: 709251718 / R_kgDOKkZShg