From a8550ad4bc120e5dd8274d1ff19964b8c4b92a7e Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Thu, 18 Jun 2026 11:07:43 -0700 Subject: [PATCH] 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. --- stacks/comfyui/compose.yaml | 13 +++++++++---- stacks/parakeet/compose.yaml | 2 +- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/stacks/comfyui/compose.yaml b/stacks/comfyui/compose.yaml index d11454b..44a455a 100644 --- a/stacks/comfyui/compose.yaml +++ b/stacks/comfyui/compose.yaml @@ -1,8 +1,9 @@ # ComfyUI — node-based Stable Diffusion / Flux inference UI. # -# Runs on irv-ml1 (dual GPU: RTX 3090 + RTX A6000). Both GPUs are -# exposed via NVIDIA_VISIBLE_DEVICES=all so GPU selection happens -# per-workflow inside ComfyUI. +# Runs on irv-ml1 (dual GPU: RTX 3090 + RTX A6000). PINNED to the A6000 +# (device 1) via NVIDIA_VISIBLE_DEVICES=1 — the 3090 hosts the audio/TTS +# zoo (chatterbox, parakeet, vibevoice, ytvc, kokoro) so ComfyUI gets the +# full 48 GB A6000 to itself (operator consolidation 2026-06-18). # # All user state — models, workflows, custom_nodes, input, output — # lives under a single BASE_DIRECTORY tree on /worktank (462 GB @@ -30,7 +31,11 @@ services: ports: - "${COMFYUI_BIND:-0.0.0.0}:${COMFYUI_PORT}:8188" environment: - - NVIDIA_VISIBLE_DEVICES=all + - NVIDIA_VISIBLE_DEVICES=1 + # Pin torch at the current 2.12.1+cu129 so the boot script stops + # auto-upgrading it — compiled SageAttention kernels must not drift + # (comfy-dev torch-pin, operator-approved 2026-06-18). + - DISABLE_UPGRADES=true - WANTED_UID=${COMFYUI_UID} - WANTED_GID=${COMFYUI_GID} - BASE_DIRECTORY=/basedir diff --git a/stacks/parakeet/compose.yaml b/stacks/parakeet/compose.yaml index 7a0cb5d..133ddea 100644 --- a/stacks/parakeet/compose.yaml +++ b/stacks/parakeet/compose.yaml @@ -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}