praveenkumarpranjal/bifrost
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
Repositories
praveenkumarpranjal/ane-gpu
Run LLM inference across the Apple Neural Engine + GPU concurrently on Apple Silicon (drop-in MLX accelerator)
praveenkumarpranjal/omni-core
Fastest CPU inference engine for LLMs on Apple Silicon - 15 tok/s, 0.9999 correlation with PyTorch
praveenkumarpranjal/freellmapi
OpenAI-compatible proxy that aggregates free-tier keys from ~14 AI providers with automatic failover. For personal experimentation only.