inference 9
- SIE's Public Repo Is an Export Surface, Not a Workshop
- Unsloth Local API Guide: Run Claude/OpenAI-Style Clients on Your Own Machine
- LLM Serving Repositories Target Different Layers
- Qwen3.5-Medium Architecture: MoE Routing, 1M Context, and Sonnet-Class Local Inference
- The Four LLM Inference Patterns: Disaggregating Prefill and Decode Economics
- Source Audit: Hugging Face TEI and Sub-Millisecond Embedding Serving
- Source Audit: KTransformers and Heterogeneous CPU-GPU MoE Inference
- Signal-Decision Architecture: Multi-Dimensional Semantic Routing for vLLM Clusters
- Architecting Production ML Inference: From Microservices to vLLM Clusters