Add peak output tokens per second in bench_serving (#14165)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This commit is contained in:
Xiaoyu Zhang
2025-12-01 17:47:54 +08:00
committed by GitHub
co-authored by github-actions[bot] <github-actions[bot]@users.noreply.github.com>
parent 630a693081
commit 9c80072845
2 changed files with 103 additions and 1 deletions
+3 -1
View File
@@ -230,6 +230,7 @@ RUN --mount=type=cache,target=/var/cache/apt apt-get update && apt-get install -
bear \
ccache \
less \
gnuplot \
&& apt install -y rdma-core infiniband-diags openssh-server perftest ibverbs-providers libibumad3 libibverbs1 libnl-3-200 libnl-route-3-200 librdmacm1 \
&& rm -rf /var/lib/apt/lists/* \
&& apt-get clean
@@ -258,7 +259,8 @@ RUN --mount=type=cache,target=/root/.cache/pip python3 -m pip install --break-sy
pre-commit \
pandas \
matplotlib \
tabulate
tabulate \
termplotlib
# Install diff-so-fancy
RUN curl -LSso /usr/local/bin/diff-so-fancy https://${GITHUB_ARTIFACTORY}/so-fancy/diff-so-fancy/releases/download/v1.4.4/diff-so-fancy \