biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

add SLA information into comparison graph for vLLM Benchmark Suite (#25525)

Browse Source 
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
Signed-off-by: louie-tsai <louie.tsai@intel.com>
Signed-off-by: Louie Tsai <louie.tsai@intel.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Louie Tsai
2025-10-23 01:04:59 -07:00
committed by GitHub
parent 50b788a17a
commit 3b7bdf983b
7 changed files with 571 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py
View File

@@ -63,9 +63,11 @@ serving_column_mapping = {
"mean_ttft_ms": "Mean TTFT (ms)",
"median_ttft_ms": "Median TTFT (ms)",
"p99_ttft_ms": "P99 TTFT (ms)",
"std_ttft_ms": "STD TTFT (ms)",
"mean_tpot_ms": "Mean TPOT (ms)",
"median_tpot_ms": "Median",
"p99_tpot_ms": "P99",
"std_tpot_ms": "STD TPOT (ms)",
"mean_itl_ms": "Mean ITL (ms)",
"median_itl_ms": "Median ITL (ms)",
"p99_itl_ms": "P99 ITL (ms)",
@@ -368,7 +370,7 @@ if __name__ == "__main__":
# The GPUs sometimes come in format of "GPUTYPE\nGPUTYPE\n...",
# we want to turn it into "8xGPUTYPE"
df["GPU"] = df["GPU"].apply(
lambda x: f"{len(x.splitlines())}x{x.splitlines()[0]}"
lambda x: "{}x{}".format(len(x.split("\n")), x.split("\n")[0])
)
# get markdown tables