Frank
918fe4eaec
The vllmScripts repository (LLM inference fleet: serve scripts, systemd units, env tunables, deployment runbook, research docs) is merged into this repository. Its full history is grafted under llm/ with a two-parent merge commit so no commit is lost. A follow-up commit reorganizes llm/ into the repo layout: llm/docs -> docs/LLM, llm/scripts -> scripts, llm/old -> old.
37 lines
1.1 KiB
Bash
Executable File
37 lines
1.1 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Bound the ggml-rpc worker tensor cache.
|
|
#
|
|
# The worker (frank-pp-worker on Dankserver) keys cache entries per
|
|
# session, so each model load writes a fresh full copy (~15 GB). Left
|
|
# unbounded, the directory filled the root disk to 100% on 2026-08-17;
|
|
# failed cache writes left 0-byte entries, and a later reload served
|
|
# corrupt weights -> degenerate model output (see the cache incident in
|
|
# docs/Pipeline Parallelism/Qwen3.8 PP Deployment.md).
|
|
#
|
|
# This script prunes the cache to a byte cap, oldest files first. Cache
|
|
# entries are derived data: safe to delete. Run from cron on Dankserver.
|
|
set -euo pipefail
|
|
|
|
CACHE_DIR=/home/dank/.cache/llama.cpp/rpc
|
|
MAX_BYTES=$((40 * 1024 * 1024 * 1024)) # 40 GiB
|
|
|
|
if [[ ! -d "$CACHE_DIR" ]]; then
|
|
exit 0
|
|
fi
|
|
|
|
total=$(du -sb "$CACHE_DIR" | cut -f1)
|
|
if (( total <= MAX_BYTES )); then
|
|
exit 0
|
|
fi
|
|
|
|
while (( total > MAX_BYTES )); do
|
|
oldest=$(ls -1t "$CACHE_DIR" | tail -1)
|
|
if [[ -z "$oldest" ]]; then
|
|
break
|
|
fi
|
|
rm -f -- "$CACHE_DIR/$oldest"
|
|
total=$(du -sb "$CACHE_DIR" | cut -f1)
|
|
done
|
|
|
|
echo "prune-rpc-cache: pruned to $(du -sh "$CACHE_DIR" | cut -f1)"
|