vLLM vs Perplexity

FeaturevLLMPerplexity
CategoryLocal AI InfrastructureAI Search
PricingFree (open-source)Free + Pro $20/mo
GitHub Stars45,000—
PlatformsLinuxWeb, iOS, Android
Features
  • ✓ PagedAttention
  • ✓ Continuous batching
  • ✓ Tensor parallelism
  • ✓ OpenAI-compatible API
  • ✓ Multi-GPU
  • ✓ Quantization
  • ✓ Real-time search
  • ✓ Citations
  • ✓ Follow-up questions
  • ✓ File upload
  • ✓ API
  • ✓ Collections
Tags
open-sourceinferenceservinggpuhigh-throughput
searchresearchcitationswebapi