noelbautista91/llms
1
0
Fork 0
Code Activity Actions

docs: document sleep and hibernation freeze protection with systemd

Browse source
This commit is contained in:
Noel Bautista 2026-10-21 12:27:17 -07:00
parent f78402d8bf
commit 0cf685a6d2
No known key found for this signature in database
1 changed files with 15 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
docs/vram-budgeting.md
View file

@ -47,3 +47,18 @@ Using **`-ctk q8_0 -ctv q8_0`**:
- **50% Memory Reduction**: Halves KV cache memory requirements.
- **Near-Lossless Perplexity**: Q8_0 maintains >99.8% precision with no degradation in reasoning benchmarks.
- **Native ROCm Acceleration**: Supported with Flash Attention (`-fa on`).
---
## 4. Sleep & Hibernation Protection
### The Problem
On AMD ROCm architectures, entering system suspend (`systemd-suspend`), hybrid sleep, or hibernation with active ~28-30GB VRAM allocations and open `/dev/kfd` contexts causes `amdgpu` driver deadlocks, resulting in full system freezes during or immediately after sleep state transitions.
### Declarative Systemd Sleep Hook
In `dotfiles` ([`modules/nixos/gpu.nix`](file:///home/noelbautista91/Documents/Projects/dotfiles/modules/nixos/gpu.nix)), a declarative systemd service (`llama-server-sleep-stop.service`) is bound to `sleep.target`:
- Executes synchronously **before** `sleep.target`, `systemd-suspend`, and `systemd-hibernate`.
- Sends `SIGTERM` to allow clean buffer detachment, followed by a hard `SIGKILL` if processes linger.
- Flushes GPU VRAM and closes `/dev/kfd` handles before the kernel initiates D3 power state transition, preventing machine freezes.
- Once resumed, servers can be relaunched instantly with `F5` in `llm-tui` or via Rofi.