mrleo1nid/gpu-rent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor GPU environment verification tests and update CLI documentation

Browse Source 
- Rearranged the order of verification steps in the CLI documentation for clarity.
- Enhanced the `test_verify_gpu_env` tests to improve logging and error assertions, ensuring accurate feedback on GPU stack checks.
- Added a new test to skip the torch requirement when only LLM is enabled, reflecting updated behavior in GPU environment verification.
This commit is contained in:
Leonid Pershin
2026-08-21 07:00:19 +03:00
parent 3c8225a69e
commit d409e2e154
2 changed files with 44 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/cli.md
+3 -3
View File
@@ -231,9 +231,9 @@ Application credential для idle-killer CLI создаёт на `up` (узко
1. Nova `ACTIVE`
2. TCP 22 / SSH
3. На VM: HTTP сервисов стека (SwarmUI `:7801` / Ollama `:11434` / llama.cpp `:8080`) — `verify_stack_on_vm`
4. На VM: **nvidia-smi / CUDA** (+ **torch+cuda** в Comfy venv, если SwarmUI) — `verify_gpu_env`
5. Backend Idle (если SwarmUI) → toast (если `NOTIFY_READY`)
3. Backend Idle (если SwarmUI) → toast (если `NOTIFY_READY`)
4. На VM: HTTP сервисов стека (SwarmUI `:7801` / Ollama `:11434` / llama.cpp `:8080`) — `verify_stack_on_vm`
5. На VM: **nvidia-smi / CUDA** (+ **torch+cuda** в Comfy venv, если SwarmUI) — `verify_gpu_env`
6. Туннель + проверка **localhost** тех же сервисов → access-card
Локальный порт UI: **17801** (на VM по-прежнему 7801 на loopback).