Jumoke Bolanle
Jumoke Bolanle
@jbolanle
SOC analyst by day, hobbyist developer and AI explorer by night. Building tools, chasing signals, and logging the practice.
Nº 089
Workbench — Active
Local LLM context caching finally holds
For three days I've been fighting context window drift in my local Ollama setup. The model would cache correctly for the first few turns, then suddenly drop the entire context and start fresh. No error. Just silence and reset.
Index — All Entries
2026
Workbench
Local LLM context caching finally holds
#ollama#local-llm#modelfile 04.29.26