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, 04:30 UTC
[CI] Unboock H100 Benchmark (#11419)
Signed-off-by: simon-mo <simon.mo@hey.com>
Simon Mo committed
Dec 22, 2024 at 14:17 UTC
048fc57a0fb599a3e39bbc9228432b0d1bb9e88d
1 file changed
+3
-3
.buildkite/nightly-benchmarks/benchmark-pipeline.yaml
+3
-3
@@ -65,9 +65,9 @@ steps:
65
- VLLM_USAGE_SOURCE
66
- HF_TOKEN
67
68
- - block: "Run H100 Benchmark"
69
- key: block-h100
70
- depends_on: ~
68
+ #- block: "Run H100 Benchmark"
69
+ #key: block-h100
70
+ #depends_on: ~
71
72
- label: "H100"
73
# skip: "use this flag to conditionally skip the benchmark step, useful for PR testing"