A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.
Appears on
Quick read
Latest capture 2026-06-28 03:08
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
34 paths
Agent instructions and tool configuration found in this repository.
Agent instructions
Agent workspace 27
Claude Code 3
Gemini CLI 3
10 more paths detected.
4 observed captures since 2026-05-25. Observed captures are shown by default.
Stars from first capture +70
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.
A high-throughput and memory-efficient inference and serving engine for LLMs
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
Achieve state of the art inference performance with modern accelerators on Kubernetes
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
An Open-source Toolkit for LLM Development
