Enable validated prefix caching and record DGX Spark optimization benchmarks

2026-09-17 22:09:58 +08:00
parent 5f3030260e
commit 1e2f48d1a4
28 changed files with 707 additions and 8 deletions
@@ -0,0 +1,3 @@
+#!/usr/bin/env bash
+source "$(dirname -- "${BASH_SOURCE[0]}")/common.sh"
+"${compose[@]}" exec -T vllm python3 -u - --label "${1:?Usage: benchmark.sh LABEL [all|short|long]}" --phase "${2:-all}" < scripts/benchmark.py