fix(llm-inference): bitsandbytes int4 OOM — pending switch to llama.cpp+GGUF

bitsandbytes quantizes on-the-fly: loads full bf16 weights (~54GB RAM peak)
before compressing to int4. Kills the 40GB OptiPlex on torch.compile warmup.

Fix in next commit: switch serve phase to llama.cpp + GGUF Q4_K_M.
Pre-quantized weights load directly — peak RAM ~16GB, no compile overhead.

ansible/roles/llm-inference/tasks/vllm.yml

@@ -22,9 +22,11 @@
   become: true
   become_user: "{{ llm_venv_owner }}"
 
-- name: Install vLLM
+- name: Install vLLM and bitsandbytes
   ansible.builtin.pip:
-    name: vllm
+    name:
+      - vllm
+      - bitsandbytes
     state: present
     virtualenv: "{{ llm_venv_path }}"
   become: true