Downloader for Qwen-Image weights, switch-model.sh #46

2026-09-06T18:57:49Z

haylan commented

2026-09-06 18:57:49 +00:00

Two frontier tickets from the ComfyUI map (#38), both unblocked now that their blockers (#39 model choice, #40 lazytainer research) are resolved.

downloader-comfyui service (docker-compose.yml) + COMFYUI_* vars (.env.example): fetches Qwen-Image FP8 diffusion/text-encoder/VAE weights from Comfy-Org/Qwen-Image_ComfyUI, same test -f guard pattern as the existing downloaders. Closes #42.
scripts/switch-model.sh: swaps GPU residency between llama-server and comfyui via direct docker compose stop/up -d, bypassing lazytainer per docs/research/lazytainer-omniroute-idle-stop.md. llama-server-fast stays resident throughout — not part of this swap. Closes #43.
scripts/update.sh: runs the new downloader profile.

docker compose config -q validated clean.

Not done by this PR (manual, needs the real R9700 box):

Run ./scripts/update.sh on the server to actually pull the ~25GB of weights
Try ./scripts/switch-model.sh comfyui / ./scripts/switch-model.sh qwen for real and confirm the swap works, VRAM fits alongside llama-server-fast
downloader-comfyui's target path (/storage/models/...) is unconfirmed against the yurisasc/comfyui-rocm7.1 image's actual Dockerfile — same caveat already flagged on the comfyui service itself

Refs #38, closes #42, closes #43

🤖 Generated with Claude Code

https://claude.ai/code/session_01MrnMEdzeQzqZE5soVEXPCx

Two frontier tickets from the ComfyUI map (#38), both unblocked now that their blockers (#39 model choice, #40 lazytainer research) are resolved. - `downloader-comfyui` service (`docker-compose.yml`) + `COMFYUI_*` vars (`.env.example`): fetches Qwen-Image FP8 diffusion/text-encoder/VAE weights from `Comfy-Org/Qwen-Image_ComfyUI`, same `test -f` guard pattern as the existing downloaders. Closes #42. - `scripts/switch-model.sh`: swaps GPU residency between `llama-server` and `comfyui` via direct `docker compose stop`/`up -d`, bypassing lazytainer per `docs/research/lazytainer-omniroute-idle-stop.md`. `llama-server-fast` stays resident throughout — not part of this swap. Closes #43. - `scripts/update.sh`: runs the new downloader profile. `docker compose config -q` validated clean. **Not done by this PR** (manual, needs the real R9700 box): - Run `./scripts/update.sh` on the server to actually pull the ~25GB of weights - Try `./scripts/switch-model.sh comfyui` / `./scripts/switch-model.sh qwen` for real and confirm the swap works, VRAM fits alongside llama-server-fast - `downloader-comfyui`'s target path (`/storage/models/...`) is unconfirmed against the `yurisasc/comfyui-rocm7.1` image's actual Dockerfile — same caveat already flagged on the `comfyui` service itself Refs #38, closes #42, closes #43 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_01MrnMEdzeQzqZE5soVEXPCx

haylan added 1 commit 2026-09-06 18:57:49 +00:00

feat: downloader for Qwen-Image weights, switch-model.sh script 4b47a1769d

Two frontier tickets from the ComfyUI map (#38), both unblocked now
that their blockers (#39 model choice, #40 lazytainer research) are
resolved.

- downloader-comfyui service (docker-compose.yml) + COMFYUI_* vars
  (.env.example): fetches Qwen-Image FP8 diffusion/text-encoder/VAE
  weights from Comfy-Org/Qwen-Image_ComfyUI, same test -f guard
  pattern as the existing downloaders. Closes #42.
- scripts/switch-model.sh: swaps GPU residency between llama-server
  and comfyui via direct `docker compose stop`/`up -d`, bypassing
  lazytainer per docs/research/lazytainer-omniroute-idle-stop.md
  (its packet-threshold detector can't distinguish OmniRoute's health
  checks from real traffic, so idle-stop can't be relied on for a
  deliberate swap). llama-server-fast stays resident throughout —
  not part of this swap. Closes #43.
- scripts/update.sh: runs the new downloader profile.

docker compose config -q validated clean.

Refs #38, #42, #43

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MrnMEdzeQzqZE5soVEXPCx

haylan merged commit 1ee2e76033 into main

2026-09-06 19:01:02 +00:00

haylan deleted branch comfyui-model-and-switch-script

2026-09-06 19:01:03 +00:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: haylan/LLM-Server#46