Skip to content

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

Rust

chore(ci): run proxy benchmark manually (#491)

Elyas Mehtabuddin4626bd102d8f
diff --git a/.github/workflows/perf.yml b/.github/workflows/perf.yml
index 32f1209da..e73eb2798 100644
--- a/.github/workflows/perf.yml
+++ b/.github/workflows/perf.yml
@@ -1,9 +1,6 @@
-name: Perf Benchmark
+name: Perf Benchmark (manual)
on:
- pull_request:
- push:
- branches: [main]
workflow_dispatch:
inputs:
concurrency:
@@ -13,11 +10,6 @@ on:
description: "aiperf --request-count"
default: "200"
-# Cancel superseded PR runs; keep main builds.
-concurrency:
- group: ${{ github.workflow }}-${{ github.ref }}
- cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
permissions:
contents: read