xllm is a developer engineering workflows repository at jd-opensource/xllm; maintainers describe it as: A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. Its recorded primary language is C++. License metadata lists Apache-2.0. GitHub metadata shows about 1,318 stars. The project homepage is https://xllm-ai.com/.
License
Apache-2.0
Stars
1,385
Homepage
https://xllm-ai.com/Features
- Recorded summary for xllm: A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.
- xllm uses C++ as its recorded primary language, which helps with stack-fit review.
- xllm fits engineering teams assessing code, CLI, SDK, runtime, or developer-tooling workflows.
- xllm lists Apache-2.0 license metadata; review obligations before redistribution or hosted use.
- xllm has about 1,318 GitHub stars in the local metadata snapshot.
- xllm links to https://xllm-ai.com/ for homepage, docs, or demo validation.
Use Cases
- Evaluate LLM/VLM inference-engine architecture
- Compare deployment approaches across AI accelerators
- Study high-performance C++ inference implementation
- Build model-serving performance prototypes
- Inform enterprise model-serving technology selection
FAQ
Start from the repository summary (A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.), then verify maintenance status, integration boundaries, and whether its developer engineering workflows focus matches the intended workflow. Repository: https://github.com/jd-opensource/xllm. Stars: about 1,318. License: Apache-2.0. Language: C++.
xllm is best treated as a repository-level component or reference implementation for developer engineering workflows. Good evaluation scenarios include: Evaluate xllm when the need is developer engineering workflows and the repo summary matches: A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for div... Compare the C++ implementation in xllm before choosing a similar internal architecture. Use xllm to study developer-tooling implementation details before building internal workflows.