A agentindex
Comparison

LMDeploy vs vLLM

A like-for-like, spec-level comparison. Both entries are verified against their docs and repo.

LMDeploy

Efficient inference and serving for open models.

  • + Strong quantization and throughput optimizations
  • + Good support for InternLM and common open models
  • − Smaller community than vLLM
  • − Less Western documentation

vLLM

High-throughput self-hosted LLM serving engine.

  • + Industry-standard throughput and batching
  • + Broad model and hardware support
  • − Requires GPU ops expertise to run well
  • − Configuration surface is large
Spec LMDeploy vLLM
Role Inference engine Inference engine
Tags inference-engine inference-engine
License Apache-2.0 Apache-2.0
Open source Yes Yes
Self-hostable Yes Yes
MCP support No No
Pricing free free
Price Free Free
Usage cost No model cost No model cost
Models multi multi
Languages python, cpp python
GitHub stars 7.9k 85.3k
Last activity 2026-07-03 2026-07-04