comfyui(irv-ml1): add PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True

Native-allocator expandable segments to cut Qwen-Image-Edit fragmentation
OOMs on the A6000 (a ~2 GB alloc failing with 1.75 GB free while 45 GB sat
allocated + reserved-but-unallocated). Cache-preserving — packs better
without unloading the checkpoint, so no edit-latency hit. Paired with the
existing --disable-cuda-malloc (incompatible with cudaMallocAsync).

Deployed + recreated on irv-ml1; verified env present, PyTorch reads it,
container healthy. comfy-dev request 2026-06-25.

stacks/comfyui/compose.yaml

@@ -57,6 +57,14 @@ services:
       #    sm_86 build (rebuilt against the pinned torch 2.12.1). Global speedup
       #    across Flux/SDXL/Wan (comfy-dev benchmarking, 2026-06-18).
       - COMFY_CMDLINE_EXTRA=--disable-cuda-malloc --fp8_e4m3fn-text-enc --use-sage-attention
+      # Let PyTorch's native caching allocator grow segments instead of
+      # pre-carving fixed blocks — cuts fragmentation OOMs on long-lived
+      # Qwen-Image-Edit sessions (a ~2 GB alloc failing with 1.75 GB free while
+      # 45 GB sat allocated + reserved-but-unallocated). Cache-preserving: packs
+      # better WITHOUT unloading the checkpoint, so no edit-latency hit. Only
+      # valid under the native allocator (paired with --disable-cuda-malloc
+      # above; incompatible with cudaMallocAsync). comfy-dev request 2026-06-25.
+      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
     volumes:
       - ${COMFYUI_BASEDIR}:/basedir
       # models/ overlaid from storetank. The ~325 GB model tree was migrated