@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 9f9704dca6
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 15, 23:30 UTC

[perf-benchmark] cleanup unused Docker images and volumes in H100 benchmark instance (#12706)

Kevin H. Luu committed Feb 12, 2025 at 19:51 UTC 9f9704dca6dda7d4af556b133d5e42c360dd2fb0
1 file changed +6
.buildkite/nightly-benchmarks/benchmark-pipeline.yaml
+6
@@ -70,6 +70,12 @@ steps:
70 #key: block-h100
71 #depends_on: ~
72
73 + - label: "Cleanup H100"
74 + agents:
75 + queue: H100
76 + depends_on: ~
77 + command: docker system prune -a --volumes --force
78 +
79 - label: "H100"
80 # skip: "use this flag to conditionally skip the benchmark step, useful for PR testing"
81 agents: