feat(irv-ml1): pin comfyui to A6000 + torch-pin; parakeet -> 3090 (VRAM consolidation)

Operator consolidation (2026-06-18): give ComfyUI the full 48 GB A6000 and move the
audio/TTS zoo to the 3090.

- comfyui: NVIDIA_VISIBLE_DEVICES all -> 1 (A6000 only), + DISABLE_UPGRADES=true to
  pin torch at 2.12.1+cu129 so the mmartial boot script stops auto-upgrading it and
  the compiled SageAttention kernels stay matched (comfy-dev torch-pin, approved).
- parakeet: NVIDIA_VISIBLE_DEVICES all -> 0 (3090).

Other GPU reassignments are deployment-side (not repo compose): chatterbox-fast via
its .env CBF_GPU_DEVICES=0; vibevoice device_ids ["1"]->["0"] (deployed from
/worktank/vibevoice/build); yt-voice-clipper worker via its override. dia2-2b,
ace-step, csm-expressiva downed (stale/unused).

Result: A6000 = ComfyUI alone (48.3 GB free); 3090 = chatterbox + parakeet + the
on-demand audio (vibevoice/ytvc/kokoro). SageAttention rebuilt against the pinned
torch; OOM cmdline (COMFY_CMDLINE_EXTRA) preserved; /object_info still lists the 9
acceleration nodes.

This commit is contained in:

2026-06-18 11:07:43 -07:00

parent f566f61b24

commit a8550ad4bc

2 changed files with 10 additions and 5 deletions

									
										stacks/parakeet/compose.yaml
									
		+1
		-1
	
												View File
												
				@@ -29,7 +29,7 @@ services:

				    ports:

				      - "${PARAKEET_BIND:-0.0.0.0}:${PARAKEET_PORT}:8000"

				    environment:

				      - NVIDIA_VISIBLE_DEVICES=all

				      - NVIDIA_VISIBLE_DEVICES=0

				      - MODEL_DIR=/models

				      - MODEL_URL=${PARAKEET_MODEL_URL}

				      - PROVIDER=${PARAKEET_PROVIDER:-cuda}