llm, add OLLAMA_NUM_THREADS which was proposed but rejected so far.

tasks/workstation/linux/software/llm.yml

@@ -287,6 +287,7 @@
               export OLLAMA_NUM_PARALLEL={{ llm_parallel }} # default is 1 and applies per-model (unconfirmed)
               export OLLAMA_CONTEXT_LENGTH={{ llm_context }} # default is 4096, https://docs.ollama.com/faq#how-can-i-specify-the-context-window-size
               export OLLAMA_MAX_QUEUE=999 # default is 512 (unconfirmed)
+              export OLLAMA_NUM_THREADS={{ (ansible_processor_vcpus / 2) | int }} # not real, but maybe some day.
 
               ### Prevent Data Loss ###
               # OLLAMA_NOPRUNE