Fix review P2s: lockfile, model path convention, trap robustness

- Regenerate uv.lock after adding fastapi/uvicorn deps so uv sync
  --locked no longer fails
- B3 scripts: default MODEL to $HOME/models/... matching documented
  convention and other launch scripts (repo has no models/ directory)
- launch_elastic_p2p: append || true to each trap command so set -e
  doesn't abort cleanup when jobs -p is empty and EngineCore orphans
  remain
This commit is contained in:
2026-05-26 16:05:43 +08:00
parent dc6d24d1ca
commit 3fdcec9c0f
4 changed files with 223 additions and 3 deletions

View File

@@ -13,7 +13,7 @@ set -euo pipefail
ROOT="${ROOT:-$(cd "$(dirname "$0")/.." && pwd)}"
VENV="$ROOT/.venv/bin"
MODEL="${MODEL:-$ROOT/models/Qwen/Qwen3-Coder-30B-A3B-Instruct}"
MODEL="${MODEL:-$HOME/models/Qwen/Qwen3-Coder-30B-A3B-Instruct}"
PROXY_PORT="${PROXY_PORT:-9300}"
BASE_PORT="${BASE_PORT:-8000}"
GPU_INDICES="${GPU_INDICES:-0 1 2 3 4 5 6 7}"

View File

@@ -16,7 +16,7 @@ set -euo pipefail
ROOT="${ROOT:-$(cd "$(dirname "$0")/.." && pwd)}"
VENV="$ROOT/.venv/bin"
MODEL="${MODEL:-$ROOT/models/Qwen/Qwen3-Coder-30B-A3B-Instruct}"
MODEL="${MODEL:-$HOME/models/Qwen/Qwen3-Coder-30B-A3B-Instruct}"
TRACE="${TRACE:-$ROOT/traces/w600_r0.0015_st30.jsonl}"
OUTDIR="${OUTDIR:-$ROOT/outputs/b3_sweep_$(date +%Y%m%d_%H%M%S)}"
PROXY_PORT="${PROXY_PORT:-9300}"

View File

@@ -27,7 +27,7 @@ PROXY_PORT=9090
HEAVY_THRESHOLD="${HEAVY_THRESHOLD:-20000}"
MAX_OFFLOAD="${MAX_OFFLOAD:-4}"
trap 'echo "Cleaning up..."; kill $(jobs -p) 2>/dev/null; pkill -9 -f "vllm serve" 2>/dev/null; pkill -9 -f "EngineCore" 2>/dev/null; pkill -9 -f cache_aware_proxy 2>/dev/null; wait 2>/dev/null' EXIT INT TERM
trap 'echo "Cleaning up..."; kill $(jobs -p) 2>/dev/null || true; pkill -9 -f "vllm serve" 2>/dev/null || true; pkill -9 -f "EngineCore" 2>/dev/null || true; pkill -9 -f cache_aware_proxy 2>/dev/null || true; wait 2>/dev/null || true' EXIT INT TERM
echo "=== Elastic P2P Offload (${N_INSTANCES}× TP=1 kv_both) ==="
echo " Model: $MODEL"