env(yaml): CCCL buddy_allocator pattern — PYTORCH_CUDA_ALLOC_CONF + OMP_NUM_THREADS

CCCL buddy_allocator.cu teaches: control memory block fragmentation
at the allocator level. Sub168 OOM trace shows 'max_split_size_mb'
suggestion. Adding PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:512
prevents PyTorch memory fragmentation that caused Sub168's final OOM.

OMP_NUM_THREADS=1 matches Sub168 docker log:
  'Reducing Torch parallelism from 64 threads to 1'

CCCL device_reduce policy_selector pattern: hardware-adaptive params
through environment, not code changes. computility-run.yaml env vars
are the serving-safe equivalent of CCCL policy_selector.

computility-run.yaml

@@ -51,3 +51,7 @@ env:
       value: /tmp/vllm-request-metrics.jsonl
     - name: VLLM_CACHE_BLOCK_SIZE
       value: '16'
+    - name: PYTORCH_CUDA_ALLOC_CONF
+      value: max_split_size_mb:512
+    - name: OMP_NUM_THREADS
+      value: '1'