Inference
Local inference pipelines, model selection, quantization, and durable orchestration.
Inference
2026-03-24· revised 2026-09-29
Checkpointing LLM chains with Temporal
Multi-step LLM inference chains are structurally fragile. Temporal workflow durability turns retry-from-scratch into replay-from-checkpoint.
Inference
2026-03-15· revised 2026-09-28
Choosing local LLMs for a two-model pipeline
Model selection, quantization, and LM Studio configuration for a two-model inference pipeline on 32 GB of VRAM.