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 17, 00:30 UTC
[CI] Add nightly benchmarks (#5260)
Simon Mo committed
Jun 5, 2024 at 11:42 UTC
d5b1eb081e193c54ac21390a0f6ba7013e4f3b11
2 files changed
+65
.buildkite/nightly-benchmarks/kickoff-pipeline.sh
new
+26
@@ -0,0 +1,26 @@
1
+#!/usr/bin/env bash
2
+
3
+set -euo pipefail
4
+
5
+# Install system packages
6
+apt update
7
+apt install -y curl jq
8
+
9
+# Install minijinja for templating
10
+curl -sSfL https://github.com/mitsuhiko/minijinja/releases/latest/download/minijinja-cli-installer.sh | sh
11
+source $HOME/.cargo/env
12
+
13
+# If BUILDKITE_PULL_REQUEST != "false", then we check the PR labels using curl and jq
14
+if [ "$BUILDKITE_PULL_REQUEST" != "false" ]; then
15
+ PR_LABELS=$(curl -s "https://api.github.com/repos/vllm-project/vllm/pulls/$BUILDKITE_PULL_REQUEST" | jq -r '.labels[].name')
16
+
17
+ if [[ $PR_LABELS == *"perf-benchmarks"* ]]; then
18
+ echo "This PR has the 'perf-benchmarks' label. Proceeding with the nightly benchmarks."
19
+ else
20
+ echo "This PR does not have the 'perf-benchmarks' label. Skipping the nightly benchmarks."
21
+ exit 0
22
+ fi
23
+fi
24
+
25
+# Upload sample.yaml
26
+buildkite-agent pipeline upload .buildkite/nightly-benchmarks/sample.yaml
.buildkite/nightly-benchmarks/sample.yaml
new
+39
@@ -0,0 +1,39 @@
1
+steps:
2
+ # NOTE(simon): You can create separate blocks for different jobs
3
+ - label: "A100: NVIDIA SMI"
4
+ agents:
5
+ queue: A100
6
+ plugins:
7
+ - kubernetes:
8
+ podSpec:
9
+ containers:
10
+ # - image: us-central1-docker.pkg.dev/vllm-405802/vllm-ci-test-repo/vllm-test:$BUILDKITE_COMMIT
11
+ # TODO(simon): check latest main branch or use the PR image.
12
+ - image: us-central1-docker.pkg.dev/vllm-405802/vllm-ci-test-repo/vllm-test:45c35f0d58f4508bf43bd6af1d3d0d0ec0c915e6
13
+ command:
14
+ - bash -c 'nvidia-smi && nvidia-smi topo -m && pwd && ls'
15
+ resources:
16
+ limits:
17
+ nvidia.com/gpu: 8
18
+ volumeMounts:
19
+ - name: devshm
20
+ mountPath: /dev/shm
21
+ nodeSelector:
22
+ nvidia.com/gpu.product: NVIDIA-A100-SXM4-80GB
23
+ volumes:
24
+ - name: devshm
25
+ emptyDir:
26
+ medium: Memory
27
+ # TODO(simon): bring H100 online
28
+ # - label: "H100: NVIDIA SMI"
29
+ # agents:
30
+ # queue: H100
31
+ # plugins:
32
+ # - docker#v5.11.0:
33
+ # image: us-central1-docker.pkg.dev/vllm-405802/vllm-ci-test-repo/vllm-test:45c35f0d58f4508bf43bd6af1d3d0d0ec0c915e6
34
+ # command:
35
+ # - bash -c 'nvidia-smi && nvidia-smi topo -m'
36
+ # propagate-environment: true
37
+ # ipc: host
38
+ # gpus: all
39
+