@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 67d745cc68
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 16, 19:30 UTC

[CI] Temporarily turn off H100 performance benchmark (#7104)

Kuntai Du committed Aug 2, 2024 at 23:52 UTC 67d745cc68d9ad31bf683a88f00a1aee9782f541
1 file changed +16 -16
.buildkite/nightly-benchmarks/benchmark-pipeline.yaml
+16 -16
@@ -42,20 +42,20 @@ steps:
42 - name: devshm
43 emptyDir:
44 medium: Memory
45 - - label: "H100"
46 - agents:
47 - queue: H100
48 - plugins:
49 - - docker#v5.11.0:
50 - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
51 - command:
52 - - bash
53 - - .buildkite/nightly-benchmarks/run-benchmarks-suite.sh
54 - mount-buildkite-agent: true
55 - propagate-environment: true
56 - ipc: host
57 - gpus: all
58 - environment:
59 - - VLLM_USAGE_SOURCE
60 - - HF_TOKEN
45 + # - label: "H100"
46 + # agents:
47 + # queue: H100
48 + # plugins:
49 + # - docker#v5.11.0:
50 + # image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
51 + # command:
52 + # - bash
53 + # - .buildkite/nightly-benchmarks/run-benchmarks-suite.sh
54 + # mount-buildkite-agent: true
55 + # propagate-environment: true
56 + # ipc: host
57 + # gpus: all
58 + # environment:
59 + # - VLLM_USAGE_SOURCE
60 + # - HF_TOKEN
61