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, 23:15 UTC
[Misc] Fix typo (#5618)
Cyrus Leung committed
Jun 18, 2024 at 11:58 UTC
32c86e494a49dff8d1d4b10c5922a36daa6e8faf
1 file changed
+1
-1
.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py
+1
-1
@@ -21,7 +21,7 @@ latency_column_mapping = {
21
"P99": "P99",
22
}
23
24
-# thoughput tests and the keys that will be printed into markdown
24
+# throughput tests and the keys that will be printed into markdown
25
throughput_results = []
26
throughput_results_column_mapping = {
27
"test_name": "Test name",