russ.fugl.dev / embed-stack
Routing embedding stack for Qwen3-Embedding-0.6B on Apple Silicon: orchestrator + MLX + llama.cpp backends
Star
Fork 0
Watch
embed-stack mlx-embed-server Sources EmbedServer
10 files
Batching.swift
Buckets.swift
DTO.swift
EmbedServerMain.swift
EmbedService.swift
HFTokenizerLoader.swift
ModelRegistry.swift
Prompt.swift
Server.swift
Warmup.swift