Rapid-MLX
Python Mediumraullenchai/Rapid-MLX
129 stars
67 forks
17 open issues
Active Apr 2026
Beginner-Friendly Issues 17
Issues tagged for new contributors
enhancement good first issue
feat: migrate DeepSeek R1 reasoning parser to OutputRouter (token-level)
#65 · Apr 6, 2026
enhancement good first issue
feat: migrate Qwen3 reasoning parser to OutputRouter (token-level)
#64 · Apr 6, 2026
enhancement good first issue
feat: migrate legacy reasoning/tool parsers to token-level OutputRouter
#63 · Apr 6, 2026
enhancement good first issue
Add benchmarking script for comparing with Ollama
#56 · Mar 26, 2026
documentation help wanted good first issue
Add Dockerfile for easy deployment
#55 · Mar 26, 2026
enhancement help wanted good first issue
Support GGUF model loading
#54 · Mar 26, 2026
enhancement help wanted
Add health check endpoint at /health
#53 · Mar 26, 2026
enhancement help wanted good first issue
Add /v1/completions token usage tracking
#52 · Mar 26, 2026
bug help wanted good first issue
Add request logging middleware
#51 · Mar 26, 2026
enhancement help wanted good first issue
Add --log-level CLI flag
#50 · Mar 26, 2026
enhancement help wanted good first issue
Add /v1/embeddings endpoint
#49 · Mar 26, 2026
enhancement help wanted good first issue
Test Rapid-MLX with more AI clients and report results
#47 · Mar 23, 2026
documentation help wanted good first issue
Document streaming JSON mode limitation
#46 · Mar 23, 2026
bug help wanted good first issue
Add CORS middleware for browser-based clients
#45 · Mar 23, 2026
enhancement good first issue
Add logprobs support to chat completions
#44 · Mar 23, 2026
enhancement help wanted good first issue