[CI/Build] Add nightly benchmarking for tgi, tensorrt-llm and lmdeploy (#5362)
This commit is contained in:
Kuntai Du
GitHub
parent
2d23b42d92
commit
a4feba929b
@ -1,5 +1,6 @@
|
||||
# vLLM benchmark suite
|
||||
|
||||
|
||||
## Introduction
|
||||
|
||||
This directory contains the performance benchmarking CI for vllm.
|
||||
|
||||
@ -1,27 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
# NOTE(simon): this script runs inside a buildkite agent with CPU only access.
|
||||
set -euo pipefail
|
||||
|
||||
# Install system packages
|
||||
apt update
|
||||
apt install -y curl jq
|
||||
|
||||
# Install minijinja for templating
|
||||
curl -sSfL https://github.com/mitsuhiko/minijinja/releases/latest/download/minijinja-cli-installer.sh | sh
|
||||
source $HOME/.cargo/env
|
||||
|
||||
# If BUILDKITE_PULL_REQUEST != "false", then we check the PR labels using curl and jq
|
||||
if [ "$BUILDKITE_PULL_REQUEST" != "false" ]; then
|
||||
PR_LABELS=$(curl -s "https://api.github.com/repos/vllm-project/vllm/pulls/$BUILDKITE_PULL_REQUEST" | jq -r '.labels[].name')
|
||||
|
||||
if [[ $PR_LABELS == *"perf-benchmarks"* ]]; then
|
||||
echo "This PR has the 'perf-benchmarks' label. Proceeding with the nightly benchmarks."
|
||||
else
|
||||
echo "This PR does not have the 'perf-benchmarks' label. Skipping the nightly benchmarks."
|
||||
exit 0
|
||||
fi
|
||||
fi
|
||||
|
||||
# Upload sample.yaml
|
||||
buildkite-agent pipeline upload .buildkite/nightly-benchmarks/benchmark-pipeline.yaml
|
||||
45
.buildkite/nightly-benchmarks/nightly-descriptions.md
Normal file
45
.buildkite/nightly-benchmarks/nightly-descriptions.md
Normal file
@ -0,0 +1,45 @@
|
||||
|
||||
# Nightly benchmark
|
||||
|
||||
The main goal of this benchmarking is two-fold:
|
||||
- Performance clarity: Provide clarity on which one (vllm, tensorrt-llm, lmdeploy and tgi) leads in performance in what workload.
|
||||
- Reproducible: one can run the exact same set of benchmarking commands inside the exact same docker by following reproducing instructions in [reproduce.md]().
|
||||
|
||||
|
||||
## Docker images
|
||||
|
||||
We benchmark vllm, tensorrt-llm, lmdeploy and tgi using the following docker images:
|
||||
- vllm/vllm-openai:v0.5.0.post1
|
||||
- nvcr.io/nvidia/tritonserver:24.04-trtllm-python-py3
|
||||
- openmmlab/lmdeploy:v0.5.0
|
||||
- ghcr.io/huggingface/text-generation-inference:2.1
|
||||
|
||||
<!-- Please check <a href="artifact://workspace/build/buildkite/vllm/performance-benchmark/.buildkite/nightly-benchmarks/nightly-pipeline.yaml">nightly-pipeline.yaml</a> artifact for more details on how we deploy the docker images. -->
|
||||
|
||||
|
||||
## Hardware
|
||||
|
||||
One AWS node with 8x NVIDIA A100 GPUs.
|
||||
|
||||
|
||||
## Workload description
|
||||
|
||||
We benchmark vllm, tensorrt-llm, lmdeploy and tgi using the following workload:
|
||||
|
||||
- Input length: randomly sample 500 prompts from ShareGPT dataset (with fixed random seed).
|
||||
- Output length: the corresponding output length of these 500 prompts.
|
||||
- Models: llama-3 8B, llama-3 70B, mixtral 8x7B.
|
||||
- Average QPS (query per second): 4 for the small model (llama-3 8B) and 2 for other two models. For each QPS, the arrival time of each query is determined using a random Poisson process (with fixed random seed).
|
||||
- Evaluation metrics: Throughput (higher the better), TTFT (time to the first token, lower the better), ITL (inter-token latency, lower the better).
|
||||
|
||||
<!-- Check <a href="artifact://workspace/build/buildkite/vllm/performance-benchmark/.buildkite/nightly-benchmarks/tests/nightly-tests.json">nightly-tests.json</a> artifact for more details. -->
|
||||
|
||||
## Plots
|
||||
|
||||
In the following plots, the dot shows the mean and the error bar shows the standard error of the mean. Value 0 means that the corresponding benchmark crashed.
|
||||
|
||||
<img src="artifact://nightly_results.png" alt="Benchmarking results" height=250 >
|
||||
|
||||
## Results
|
||||
|
||||
{nightly_results_benchmarking_table}
|
||||
120
.buildkite/nightly-benchmarks/nightly-pipeline.yaml
Normal file
120
.buildkite/nightly-benchmarks/nightly-pipeline.yaml
Normal file
@ -0,0 +1,120 @@
|
||||
common_pod_spec: &common_pod_spec
|
||||
priorityClassName: perf-benchmark
|
||||
nodeSelector:
|
||||
nvidia.com/gpu.product: NVIDIA-A100-SXM4-80GB
|
||||
volumes:
|
||||
- name: devshm
|
||||
emptyDir:
|
||||
medium: Memory
|
||||
- name: hf-cache
|
||||
hostPath:
|
||||
path: /root/.cache/huggingface
|
||||
type: Directory
|
||||
|
||||
common_container_settings: &common_container_settings
|
||||
command:
|
||||
- bash .buildkite/nightly-benchmarks/run-nightly-suite.sh
|
||||
resources:
|
||||
limits:
|
||||
nvidia.com/gpu: 8
|
||||
volumeMounts:
|
||||
- name: devshm
|
||||
mountPath: /dev/shm
|
||||
- name: hf-cache
|
||||
mountPath: /root/.cache/huggingface
|
||||
env:
|
||||
- name: VLLM_USAGE_SOURCE
|
||||
value: ci-test
|
||||
- name: HF_HOME
|
||||
value: /root/.cache/huggingface
|
||||
- name: VLLM_SOURCE_CODE_LOC
|
||||
value: /workspace/build/buildkite/vllm/performance-benchmark
|
||||
- name: HF_TOKEN
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: hf-token-secret
|
||||
key: token
|
||||
|
||||
steps:
|
||||
- block: ":rocket: Ready for comparing vllm against alternatives? This will take 4 hours."
|
||||
- label: "A100 trt benchmark"
|
||||
priority: 100
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
<<: *common_pod_spec
|
||||
containers:
|
||||
- image: nvcr.io/nvidia/tritonserver:24.04-trtllm-python-py3
|
||||
<<: *common_container_settings
|
||||
|
||||
- label: "A100 lmdeploy benchmark"
|
||||
priority: 100
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
<<: *common_pod_spec
|
||||
containers:
|
||||
- image: openmmlab/lmdeploy:v0.5.0
|
||||
<<: *common_container_settings
|
||||
|
||||
|
||||
- label: "A100 vllm benchmark"
|
||||
priority: 100
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
<<: *common_pod_spec
|
||||
containers:
|
||||
- image: vllm/vllm-openai:latest
|
||||
<<: *common_container_settings
|
||||
|
||||
- label: "A100 tgi benchmark"
|
||||
priority: 100
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
<<: *common_pod_spec
|
||||
containers:
|
||||
- image: ghcr.io/huggingface/text-generation-inference:2.1
|
||||
<<: *common_container_settings
|
||||
|
||||
- wait
|
||||
|
||||
- label: "Plot"
|
||||
priority: 100
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
<<: *common_pod_spec
|
||||
containers:
|
||||
- image: vllm/vllm-openai:v0.5.0.post1
|
||||
command:
|
||||
- bash .buildkite/nightly-benchmarks/scripts/nightly-annotate.sh
|
||||
resources:
|
||||
limits:
|
||||
nvidia.com/gpu: 8
|
||||
volumeMounts:
|
||||
- name: devshm
|
||||
mountPath: /dev/shm
|
||||
env:
|
||||
- name: VLLM_USAGE_SOURCE
|
||||
value: ci-test
|
||||
- name: VLLM_SOURCE_CODE_LOC
|
||||
value: /workspace/build/buildkite/vllm/performance-benchmark
|
||||
- name: HF_TOKEN
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: hf-token-secret
|
||||
key: token
|
||||
|
||||
- wait
|
||||
76
.buildkite/nightly-benchmarks/run-nightly-suite.sh
Normal file
76
.buildkite/nightly-benchmarks/run-nightly-suite.sh
Normal file
@ -0,0 +1,76 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -o pipefail
|
||||
set -x
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
check_hf_token() {
|
||||
# check if HF_TOKEN is available and valid
|
||||
if [[ -z "$HF_TOKEN" ]]; then
|
||||
echo "Error: HF_TOKEN is not set."
|
||||
exit 1
|
||||
elif [[ ! "$HF_TOKEN" =~ ^hf_ ]]; then
|
||||
echo "Error: HF_TOKEN does not start with 'hf_'."
|
||||
exit 1
|
||||
else
|
||||
echo "HF_TOKEN is set and valid."
|
||||
fi
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
check_gpus
|
||||
check_hf_token
|
||||
|
||||
df -h
|
||||
|
||||
(which wget && which curl) || (apt-get update && apt-get install -y wget curl)
|
||||
(which jq) || (apt-get update && apt-get -y install jq)
|
||||
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
|
||||
|
||||
|
||||
# run lmdeploy
|
||||
if which lmdeploy >/dev/null; then
|
||||
echo "lmdeploy is available, redirect to run-lmdeploy-nightly.sh"
|
||||
bash ../.buildkite/nightly-benchmarks/scripts/run-lmdeploy-nightly.sh
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# run tgi
|
||||
if [ -e /tgi-entrypoint.sh ]; then
|
||||
echo "tgi is available, redirect to run-tgi-nightly.sh"
|
||||
bash ../.buildkite/nightly-benchmarks/scripts/run-tgi-nightly.sh
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# run trt
|
||||
if which trtllm-build >/dev/null; then
|
||||
echo "trtllm is available, redirect to run-trt-nightly.sh"
|
||||
bash ../.buildkite/nightly-benchmarks/scripts/run-trt-nightly.sh
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# run vllm
|
||||
if [ -e /vllm-workspace ]; then
|
||||
echo "vllm is available, redirect to run-vllm-nightly.sh"
|
||||
bash ../.buildkite/nightly-benchmarks/scripts/run-vllm-nightly.sh
|
||||
exit 0
|
||||
fi
|
||||
|
||||
}
|
||||
|
||||
main "$@"
|
||||
26
.buildkite/nightly-benchmarks/scripts/download-tokenizer.py
Normal file
26
.buildkite/nightly-benchmarks/scripts/download-tokenizer.py
Normal file
@ -0,0 +1,26 @@
|
||||
import argparse
|
||||
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
|
||||
def main(model, cachedir):
|
||||
# Load the tokenizer and save it to the specified directory
|
||||
tokenizer = AutoTokenizer.from_pretrained(model)
|
||||
tokenizer.save_pretrained(cachedir)
|
||||
print(f"Tokenizer saved to {cachedir}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Download and save Hugging Face tokenizer")
|
||||
parser.add_argument("--model",
|
||||
type=str,
|
||||
required=True,
|
||||
help="Name of the model")
|
||||
parser.add_argument("--cachedir",
|
||||
type=str,
|
||||
required=True,
|
||||
help="Directory to save the tokenizer")
|
||||
|
||||
args = parser.parse_args()
|
||||
main(args.model, args.cachedir)
|
||||
@ -0,0 +1,6 @@
|
||||
from lmdeploy.serve.openai.api_client import APIClient
|
||||
|
||||
api_client = APIClient("http://localhost:8000")
|
||||
model_name = api_client.available_models[0]
|
||||
|
||||
print(model_name)
|
||||
102
.buildkite/nightly-benchmarks/scripts/launch-trt-server.sh
Normal file
102
.buildkite/nightly-benchmarks/scripts/launch-trt-server.sh
Normal file
@ -0,0 +1,102 @@
|
||||
#!/bin/bash
|
||||
|
||||
|
||||
server_params=$1
|
||||
common_params=$2
|
||||
|
||||
|
||||
|
||||
model_path=$(echo "$common_params" | jq -r '.model')
|
||||
model_name="${model_path#*/}"
|
||||
model_type=$(echo "$server_params" | jq -r '.model_type')
|
||||
model_dtype=$(echo "$server_params" | jq -r '.model_dtype')
|
||||
model_tp_size=$(echo "$common_params" | jq -r '.tp')
|
||||
max_batch_size=$(echo "$server_params" | jq -r '.max_batch_size')
|
||||
max_input_len=$(echo "$server_params" | jq -r '.max_input_len')
|
||||
max_output_len=$(echo "$server_params" | jq -r '.max_output_len')
|
||||
trt_llm_version=$(echo "$server_params" | jq -r '.trt_llm_version')
|
||||
|
||||
cd ~
|
||||
rm -rf models
|
||||
mkdir -p models
|
||||
cd models
|
||||
models_dir=$(pwd)
|
||||
trt_model_path=${models_dir}/${model_name}-trt-ckpt
|
||||
trt_engine_path=${models_dir}/${model_name}-trt-engine
|
||||
|
||||
cd ~
|
||||
rm -rf tensorrt-demo
|
||||
git clone https://github.com/neuralmagic/tensorrt-demo.git
|
||||
cd tensorrt-demo
|
||||
tensorrt_demo_dir=$(pwd)
|
||||
|
||||
# make sure the parameter inside tensorrt_demo is consistent to envvar
|
||||
sed -i.bak "/key: \"tokenizer_dir\"/,/string_value:/s|string_value: \".*\"|string_value: \"$model_path\"|" ./triton_model_repo/postprocessing/config.pbtxt
|
||||
sed -i.bak "/key: \"tokenizer_dir\"/,/string_value:/s|string_value: \".*\"|string_value: \"$model_path\"|" ./triton_model_repo/preprocessing/config.pbtxt
|
||||
sed -i.bak "s|\(max_batch_size:\s*\)[0-9]*|\1$max_batch_size|g" ./triton_model_repo/ensemble/config.pbtxt
|
||||
sed -i.bak "s|\(max_batch_size:\s*\)[0-9]*|\1$max_batch_size|g" ./triton_model_repo/preprocessing/config.pbtxt
|
||||
sed -i.bak "s|\(max_batch_size:\s*\)[0-9]*|\1$max_batch_size|g" ./triton_model_repo/postprocessing/config.pbtxt
|
||||
sed -i.bak "s|\(max_batch_size:\s*\)[0-9]*|\1$max_batch_size|g" ./triton_model_repo/tensorrt_llm_bls/config.pbtxt
|
||||
|
||||
|
||||
cd /
|
||||
rm -rf tensorrtllm_backend
|
||||
git clone https://github.com/triton-inference-server/tensorrtllm_backend.git
|
||||
git lfs install
|
||||
cd tensorrtllm_backend
|
||||
git checkout $trt_llm_version
|
||||
tensorrtllm_backend_dir=$(pwd)
|
||||
git submodule update --init --recursive
|
||||
cp -r ${tensorrt_demo_dir}/triton_model_repo ${tensorrtllm_backend_dir}/
|
||||
|
||||
cd /tensorrtllm_backend
|
||||
cd ./tensorrt_llm/examples/${model_type}
|
||||
|
||||
|
||||
if echo "$common_params" | jq -e 'has("fp8")' > /dev/null; then
|
||||
|
||||
echo "Key 'fp8' exists in common params. Use quantize.py instead of convert_checkpoint.py"
|
||||
echo "Reference: https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/llama/README.md"
|
||||
python ../quantization/quantize.py \
|
||||
--model_dir ${model_path} \
|
||||
--dtype ${model_dtype} \
|
||||
--tp_size ${model_tp_size} \
|
||||
--output_dir ${trt_model_path} \
|
||||
--qformat fp8 \
|
||||
--kv_cache_dtype fp8 \
|
||||
--calib_size 2
|
||||
|
||||
else
|
||||
|
||||
echo "Key 'fp8' does not exist in common params. Use convert_checkpoint.py"
|
||||
python3 convert_checkpoint.py \
|
||||
--model_dir ${model_path} \
|
||||
--dtype ${model_dtype} \
|
||||
--tp_size ${model_tp_size} \
|
||||
--output_dir ${trt_model_path}
|
||||
|
||||
fi
|
||||
|
||||
|
||||
|
||||
trtllm-build \
|
||||
--checkpoint_dir=${trt_model_path} \
|
||||
--gpt_attention_plugin=${model_dtype} \
|
||||
--gemm_plugin=${model_dtype} \
|
||||
--remove_input_padding=enable \
|
||||
--paged_kv_cache=enable \
|
||||
--tp_size=${model_tp_size} \
|
||||
--max_batch_size=${max_batch_size} \
|
||||
--max_input_len=${max_input_len} \
|
||||
--max_output_len=${max_output_len} \
|
||||
--max_num_tokens=${max_output_len} \
|
||||
--opt_num_tokens=${max_output_len} \
|
||||
--output_dir=${trt_engine_path}
|
||||
|
||||
cd /tensorrtllm_backend/triton_model_repo
|
||||
rm -rf ./tensorrt_llm/1/*
|
||||
cp -r ${trt_engine_path}/* ./tensorrt_llm/1
|
||||
cd /tensorrtllm_backend
|
||||
python3 scripts/launch_triton_server.py \
|
||||
--world_size=${model_tp_size} \
|
||||
--model_repo=/tensorrtllm_backend/triton_model_repo &
|
||||
40
.buildkite/nightly-benchmarks/scripts/nightly-annotate.sh
Normal file
40
.buildkite/nightly-benchmarks/scripts/nightly-annotate.sh
Normal file
@ -0,0 +1,40 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -ex
|
||||
set -o pipefail
|
||||
|
||||
|
||||
main() {
|
||||
|
||||
(which wget && which curl) || (apt-get update && apt-get install -y wget curl)
|
||||
(which jq) || (apt-get update && apt-get -y install jq)
|
||||
|
||||
if [ ! -f /workspace/buildkite-agent ]; then
|
||||
echo "buildkite-agent binary not found. Skip plotting the results."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# initial annotation
|
||||
description="$VLLM_SOURCE_CODE_LOC/.buildkite/nightly-benchmarks/nightly-descriptions.md"
|
||||
|
||||
# download results
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
mkdir -p results/
|
||||
/workspace/buildkite-agent artifact download 'results/*nightly_results.json' results/
|
||||
ls
|
||||
ls results/
|
||||
|
||||
# generate figures
|
||||
python3 -m pip install tabulate pandas matplotlib
|
||||
python3 $VLLM_SOURCE_CODE_LOC/.buildkite/nightly-benchmarks/scripts/plot-nightly-results.py \
|
||||
--description $description \
|
||||
--results-folder results/
|
||||
|
||||
# upload results and figures
|
||||
/workspace/buildkite-agent artifact upload "nightly_results.png"
|
||||
/workspace/buildkite-agent artifact upload $VLLM_SOURCE_CODE_LOC/.buildkite/nightly-benchmarks/nightly-pipeline.yaml
|
||||
/workspace/buildkite-agent artifact upload $VLLM_SOURCE_CODE_LOC/.buildkite/nightly-benchmarks/tests/nightly-tests.json
|
||||
/workspace/buildkite-agent annotate --style "success" --context "nightly-benchmarks-results" --append < nightly_results.md
|
||||
}
|
||||
|
||||
main "$@"
|
||||
135
.buildkite/nightly-benchmarks/scripts/plot-nightly-results.py
Normal file
135
.buildkite/nightly-benchmarks/scripts/plot-nightly-results.py
Normal file
@ -0,0 +1,135 @@
|
||||
import argparse
|
||||
import json
|
||||
import math
|
||||
from pathlib import Path
|
||||
|
||||
import matplotlib.pyplot as plt
|
||||
import pandas as pd
|
||||
from tabulate import tabulate
|
||||
|
||||
|
||||
def parse_arguments():
|
||||
parser = argparse.ArgumentParser(
|
||||
description=
|
||||
'Parse command line arguments for summary-nightly-results script.')
|
||||
parser.add_argument('--results-folder',
|
||||
type=str,
|
||||
required=True,
|
||||
help='The folder where the results are stored.')
|
||||
parser.add_argument('--description',
|
||||
type=str,
|
||||
required=True,
|
||||
help='Description of the results.')
|
||||
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
def main(args):
|
||||
bar_colors = ['#56B4E9', '#009E73', '#D55E00', '#E69F00']
|
||||
results_folder = Path(args.results_folder)
|
||||
|
||||
results = []
|
||||
|
||||
# collect results
|
||||
for test_file in results_folder.glob("*_nightly_results.json"):
|
||||
with open(test_file, "r") as f:
|
||||
results = results + json.loads(f.read())
|
||||
|
||||
# generate markdown table
|
||||
df = pd.DataFrame.from_dict(results)
|
||||
|
||||
md_table = tabulate(df, headers='keys', tablefmt='pipe', showindex=False)
|
||||
|
||||
with open(args.description, "r") as f:
|
||||
description = f.read()
|
||||
|
||||
description = description.format(
|
||||
nightly_results_benchmarking_table=md_table)
|
||||
|
||||
with open("nightly_results.md", "w") as f:
|
||||
f.write(description)
|
||||
|
||||
plt.rcParams.update({'font.size': 20})
|
||||
|
||||
# plot results
|
||||
fig, axes = plt.subplots(3, 3, figsize=(16, 14))
|
||||
fig.subplots_adjust(hspace=1)
|
||||
methods = ["vllm", "trt", "lmdeploy", "tgi"]
|
||||
for i, model in enumerate(["llama8B", "llama70B", "mixtral8x7B"]):
|
||||
for j, metric in enumerate(["TTFT", "ITL"]):
|
||||
means, stds = [], []
|
||||
for method in methods:
|
||||
target = df['Test name'].str.contains(model)
|
||||
target = target & df['Engine'].str.contains(method)
|
||||
filtered_df = df[target]
|
||||
|
||||
if filtered_df.empty:
|
||||
means.append(0.)
|
||||
stds.append(0.)
|
||||
else:
|
||||
means.append(filtered_df[f"Mean {metric} (ms)"].values[0])
|
||||
std = filtered_df[f"Std {metric} (ms)"].values[0]
|
||||
success = filtered_df["Successful req."].values[0]
|
||||
stds.append(std / math.sqrt(success))
|
||||
|
||||
print(model, metric)
|
||||
print(means, stds)
|
||||
|
||||
ax = axes[i, j + 1]
|
||||
|
||||
bars = ax.bar(
|
||||
["vllm", "trt", "lmdeploy", "tgi"],
|
||||
means,
|
||||
yerr=stds,
|
||||
capsize=10,
|
||||
)
|
||||
for idx, bar in enumerate(bars):
|
||||
bar.set_color(bar_colors[idx])
|
||||
ax.set_ylim(bottom=0)
|
||||
|
||||
ax.set_ylabel(f"{metric} (ms)")
|
||||
ax.set_title(f"{model} {metric}")
|
||||
ax.grid(axis='y')
|
||||
|
||||
metric = "Tput"
|
||||
j = 0
|
||||
if True:
|
||||
tputs = []
|
||||
for method in methods:
|
||||
target = df['Test name'].str.contains(model)
|
||||
target = target & df['Engine'].str.contains(method)
|
||||
filtered_df = df[target]
|
||||
|
||||
if filtered_df.empty:
|
||||
tputs.append(0.)
|
||||
else:
|
||||
input_tput = filtered_df["Input Tput (tok/s)"].values[0]
|
||||
output_tput = filtered_df["Output Tput (tok/s)"].values[0]
|
||||
tputs.append(input_tput + output_tput)
|
||||
|
||||
print(model, metric)
|
||||
print(tputs)
|
||||
|
||||
ax = axes[i, j]
|
||||
|
||||
bars = ax.bar(
|
||||
["vllm", "trt", "lmdeploy", "tgi"],
|
||||
tputs,
|
||||
)
|
||||
for idx, bar in enumerate(bars):
|
||||
bar.set_color(bar_colors[idx])
|
||||
|
||||
ax.set_ylim(bottom=0)
|
||||
|
||||
ax.set_ylabel("Tput (token/s)")
|
||||
ax.set_title(f"{model} {metric}")
|
||||
ax.grid(axis='y')
|
||||
|
||||
fig.tight_layout()
|
||||
fig.savefig("nightly_results.png", bbox_inches='tight', dpi=400)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
args = parse_arguments()
|
||||
main(args)
|
||||
218
.buildkite/nightly-benchmarks/scripts/run-lmdeploy-nightly.sh
Normal file
218
.buildkite/nightly-benchmarks/scripts/run-lmdeploy-nightly.sh
Normal file
@ -0,0 +1,218 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -o pipefail
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
pkill lmdeploy || true
|
||||
# waiting for GPU processes to be fully killed
|
||||
sleep 10
|
||||
# Print the GPU memory usage
|
||||
# so that we know if all GPU processes are killed.
|
||||
gpu_memory_usage=$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i 0)
|
||||
# The memory usage should be 0 MB.
|
||||
echo "GPU 0 Memory Usage: $gpu_memory_usage MB"
|
||||
}
|
||||
|
||||
json2args() {
|
||||
# transforms the JSON string to command line args, and '_' is replaced to '-'
|
||||
# example:
|
||||
# input: { "model": "meta-llama/Llama-2-7b-chat-hf", "tensor_parallel_size": 1 }
|
||||
# output: --model meta-llama/Llama-2-7b-chat-hf --tensor-parallel-size 1
|
||||
local json_string=$1
|
||||
local args=$(
|
||||
echo "$json_string" | jq -r '
|
||||
to_entries |
|
||||
map("--" + (.key | gsub("_"; "-")) + " " + (.value | tostring)) |
|
||||
join(" ")
|
||||
'
|
||||
)
|
||||
echo "$args"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
# wait for vllm server to start
|
||||
# return 1 if vllm server crashes
|
||||
timeout 1200 bash -c '
|
||||
until curl -s localhost:8000/v1/completions > /dev/null; do
|
||||
sleep 1
|
||||
done' && return 0 || return 1
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `benchmark_serving.py`
|
||||
# $1: a json file specifying serving test cases
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# Iterate over serving tests
|
||||
jq -c '.[]' "$serving_test_file" | while read -r params; do
|
||||
# get the test name, and append the GPU type back to it.
|
||||
test_name=$(echo "$params" | jq -r '.test_name')
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# append lmdeploy to the test name
|
||||
test_name=lmdeploy_$test_name
|
||||
|
||||
# get common parameters
|
||||
common_params=$(echo "$params" | jq -r '.common_parameters')
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
dataset_name=$(echo "$common_params" | jq -r '.dataset_name')
|
||||
dataset_path=$(echo "$common_params" | jq -r '.dataset_path')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
num_prompts=$(echo "$common_params" | jq -r '.num_prompts')
|
||||
|
||||
|
||||
|
||||
# get client and server arguments
|
||||
server_params=$(echo "$params" | jq -r '.lmdeploy_server_parameters')
|
||||
client_params=$(echo "$params" | jq -r '.lmdeploy_client_parameters')
|
||||
server_args=$(json2args "$server_params")
|
||||
client_args=$(json2args "$client_params")
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# prepare tokenizer
|
||||
rm -rf /tokenizer_cache
|
||||
mkdir /tokenizer_cache
|
||||
python ../.buildkite/nightly-benchmarks/scripts/download-tokenizer.py \
|
||||
--model "$model" \
|
||||
--cachedir /tokenizer_cache
|
||||
|
||||
server_command="lmdeploy serve api_server $model \
|
||||
--tp $tp \
|
||||
--server-port $port \
|
||||
$server_args"
|
||||
|
||||
# run the server
|
||||
echo "Running test case $test_name"
|
||||
echo "Server command: $server_command"
|
||||
bash -c "$server_command" &
|
||||
|
||||
# wait until the server is alive
|
||||
wait_for_server
|
||||
if [ $? -eq 0 ]; then
|
||||
echo ""
|
||||
echo "lmdeploy server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "lmdeploy failed to start within the timeout period."
|
||||
break
|
||||
fi
|
||||
|
||||
# get model name
|
||||
model_name=$(python ../.buildkite/nightly-benchmarks/scripts/get-lmdeploy-modelname.py)
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
echo "qps was $qps"
|
||||
qps="inf"
|
||||
echo "now qps is $qps"
|
||||
fi
|
||||
|
||||
new_test_name=$test_name"_qps_"$qps
|
||||
|
||||
client_command="python3 benchmark_serving.py \
|
||||
--backend lmdeploy \
|
||||
--tokenizer /tokenizer_cache \
|
||||
--dataset-name $dataset_name \
|
||||
--dataset-path $dataset_path \
|
||||
--num-prompts $num_prompts \
|
||||
--port $port \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
--model \"$model_name\" \
|
||||
$client_args"
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
eval "$client_command"
|
||||
|
||||
# record the benchmarking commands
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
--arg engine "lmdeploy" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu,
|
||||
engine: $engine
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
done
|
||||
|
||||
# clean up
|
||||
kill_gpu_processes
|
||||
rm -rf /root/.cache/huggingface/*
|
||||
done
|
||||
}
|
||||
|
||||
|
||||
upload_to_buildkite() {
|
||||
# upload the benchmarking results to buildkite
|
||||
|
||||
# if the agent binary is not found, skip uploading the results, exit 0
|
||||
if [ ! -f /workspace/buildkite-agent ]; then
|
||||
echo "buildkite-agent binary not found. Skip uploading the results."
|
||||
return 0
|
||||
fi
|
||||
# /workspace/buildkite-agent annotate --style "success" --context "benchmark-results" --append < $RESULTS_FOLDER/${CURRENT_LLM_SERVING_ENGINE}_nightly_results.md
|
||||
/workspace/buildkite-agent artifact upload "$RESULTS_FOLDER/*"
|
||||
}
|
||||
|
||||
|
||||
main() {
|
||||
|
||||
check_gpus
|
||||
# enter vllm directory
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
BENCHMARK_ROOT=../.buildkite/nightly-benchmarks/
|
||||
|
||||
python -m pip install transformers==4.41.2
|
||||
|
||||
export CURRENT_LLM_SERVING_ENGINE=lmdeploy
|
||||
run_serving_tests $BENCHMARK_ROOT/tests/nightly-tests.json
|
||||
python -m pip install tabulate pandas
|
||||
python $BENCHMARK_ROOT/scripts/summary-nightly-results.py
|
||||
upload_to_buildkite
|
||||
|
||||
}
|
||||
|
||||
main "$@"
|
||||
216
.buildkite/nightly-benchmarks/scripts/run-tgi-nightly.sh
Normal file
216
.buildkite/nightly-benchmarks/scripts/run-tgi-nightly.sh
Normal file
@ -0,0 +1,216 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -o pipefail
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
pkill text-generation || true
|
||||
# waiting for GPU processes to be fully killed
|
||||
sleep 10
|
||||
# Print the GPU memory usage
|
||||
# so that we know if all GPU processes are killed.
|
||||
gpu_memory_usage=$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i 0)
|
||||
# The memory usage should be 0 MB.
|
||||
echo "GPU 0 Memory Usage: $gpu_memory_usage MB"
|
||||
}
|
||||
|
||||
json2args() {
|
||||
# transforms the JSON string to command line args, and '_' is replaced to '-'
|
||||
# example:
|
||||
# input: { "model": "meta-llama/Llama-2-7b-chat-hf", "tensor_parallel_size": 1 }
|
||||
# output: --model meta-llama/Llama-2-7b-chat-hf --tensor-parallel-size 1
|
||||
local json_string=$1
|
||||
local args=$(
|
||||
echo "$json_string" | jq -r '
|
||||
to_entries |
|
||||
map("--" + (.key | gsub("_"; "-")) + " " + (.value | tostring)) |
|
||||
join(" ")
|
||||
'
|
||||
)
|
||||
echo "$args"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
timeout 1200 bash -c '
|
||||
until curl -s localhost:8000/generate_stream > /dev/null; do
|
||||
sleep 1
|
||||
done' && return 0 || return 1
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `benchmark_serving.py`
|
||||
# $1: a json file specifying serving test cases
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# Iterate over serving tests
|
||||
jq -c '.[]' "$serving_test_file" | while read -r params; do
|
||||
# get the test name, and append the GPU type back to it.
|
||||
test_name=$(echo "$params" | jq -r '.test_name')
|
||||
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# append tgi to the test name
|
||||
test_name=tgi_$test_name
|
||||
|
||||
# get common parameters
|
||||
common_params=$(echo "$params" | jq -r '.common_parameters')
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
dataset_name=$(echo "$common_params" | jq -r '.dataset_name')
|
||||
dataset_path=$(echo "$common_params" | jq -r '.dataset_path')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
num_prompts=$(echo "$common_params" | jq -r '.num_prompts')
|
||||
|
||||
# get client and server arguments
|
||||
server_params=$(echo "$params" | jq -r '.tgi_server_parameters')
|
||||
client_params=$(echo "$params" | jq -r '.tgi_client_parameters')
|
||||
server_args=$(json2args "$server_params")
|
||||
client_args=$(json2args "$client_params")
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required num-shard $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
if echo "$common_params" | jq -e 'has("fp8")' > /dev/null; then
|
||||
echo "Key 'fp8' exists in common params."
|
||||
server_command="/tgi-entrypoint.sh \
|
||||
--model-id $model \
|
||||
--num-shard $tp \
|
||||
--port $port \
|
||||
--quantize fp8 \
|
||||
$server_args"
|
||||
else
|
||||
echo "Key 'fp8' does not exist in common params."
|
||||
server_command="/tgi-entrypoint.sh \
|
||||
--model-id $model \
|
||||
--num-shard $tp \
|
||||
--port $port \
|
||||
$server_args"
|
||||
fi
|
||||
|
||||
|
||||
|
||||
|
||||
# run the server
|
||||
echo "Running test case $test_name"
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
|
||||
# wait until the server is alive
|
||||
wait_for_server
|
||||
if [ $? -eq 0 ]; then
|
||||
echo ""
|
||||
echo "tgi server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "tgi failed to start within the timeout period."
|
||||
break
|
||||
fi
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
echo "qps was $qps"
|
||||
qps="inf"
|
||||
echo "now qps is $qps"
|
||||
fi
|
||||
|
||||
new_test_name=$test_name"_qps_"$qps
|
||||
|
||||
client_command="python3 benchmark_serving.py \
|
||||
--backend tgi \
|
||||
--model $model \
|
||||
--dataset-name $dataset_name \
|
||||
--dataset-path $dataset_path \
|
||||
--num-prompts $num_prompts \
|
||||
--port $port \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
$client_args"
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
eval "$client_command"
|
||||
|
||||
# record the benchmarking commands
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
--arg engine "tgi" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu,
|
||||
engine: $engine
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
done
|
||||
|
||||
# clean up
|
||||
kill_gpu_processes
|
||||
rm -rf /root/.cache/huggingface/*
|
||||
done
|
||||
}
|
||||
|
||||
|
||||
|
||||
upload_to_buildkite() {
|
||||
# upload the benchmarking results to buildkite
|
||||
|
||||
# if the agent binary is not found, skip uploading the results, exit 0
|
||||
if [ ! -f /workspace/buildkite-agent ]; then
|
||||
echo "buildkite-agent binary not found. Skip uploading the results."
|
||||
return 0
|
||||
fi
|
||||
# /workspace/buildkite-agent annotate --style "success" --context "benchmark-results" --append < $RESULTS_FOLDER/${CURRENT_LLM_SERVING_ENGINE}_nightly_results.md
|
||||
/workspace/buildkite-agent artifact upload "$RESULTS_FOLDER/*"
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
check_gpus
|
||||
# enter vllm directory
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
BENCHMARK_ROOT=../.buildkite/nightly-benchmarks/
|
||||
|
||||
export CURRENT_LLM_SERVING_ENGINE=tgi
|
||||
run_serving_tests $BENCHMARK_ROOT/tests/nightly-tests.json
|
||||
python -m pip install tabulate pandas
|
||||
python $BENCHMARK_ROOT/scripts/summary-nightly-results.py
|
||||
upload_to_buildkite
|
||||
|
||||
}
|
||||
|
||||
main "$@"
|
||||
214
.buildkite/nightly-benchmarks/scripts/run-trt-nightly.sh
Normal file
214
.buildkite/nightly-benchmarks/scripts/run-trt-nightly.sh
Normal file
@ -0,0 +1,214 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -o pipefail
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
pkill tritonserver || true
|
||||
# waiting for GPU processes to be fully killed
|
||||
sleep 20
|
||||
# Print the GPU memory usage
|
||||
# so that we know if all GPU processes are killed.
|
||||
gpu_memory_usage=$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i 0)
|
||||
# The memory usage should be 0 MB.
|
||||
echo "GPU 0 Memory Usage: $gpu_memory_usage MB"
|
||||
}
|
||||
|
||||
json2args() {
|
||||
# transforms the JSON string to command line args, and '_' is replaced to '-'
|
||||
# example:
|
||||
# input: { "model": "meta-llama/Llama-2-7b-chat-hf", "tensor_parallel_size": 1 }
|
||||
# output: --model meta-llama/Llama-2-7b-chat-hf --tensor-parallel-size 1
|
||||
local json_string=$1
|
||||
local args=$(
|
||||
echo "$json_string" | jq -r '
|
||||
to_entries |
|
||||
map("--" + (.key | gsub("_"; "-")) + " " + (.value | tostring)) |
|
||||
join(" ")
|
||||
'
|
||||
)
|
||||
echo "$args"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
timeout 1200 bash -c '
|
||||
until curl -s localhost:8000/generate_stream > /dev/null; do
|
||||
sleep 1
|
||||
done' && return 0 || return 1
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `benchmark_serving.py`
|
||||
# $1: a json file specifying serving test cases
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# Iterate over serving tests
|
||||
jq -c '.[]' "$serving_test_file" | while read -r params; do
|
||||
# get the test name, and append the GPU type back to it.
|
||||
test_name=$(echo "$params" | jq -r '.test_name')
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# append trt to the test name
|
||||
test_name=trt_$test_name
|
||||
|
||||
# get common parameters
|
||||
common_params=$(echo "$params" | jq -r '.common_parameters')
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
dataset_name=$(echo "$common_params" | jq -r '.dataset_name')
|
||||
dataset_path=$(echo "$common_params" | jq -r '.dataset_path')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
num_prompts=$(echo "$common_params" | jq -r '.num_prompts')
|
||||
|
||||
# get client and server arguments
|
||||
server_params=$(echo "$params" | jq -r '.trt_server_parameters')
|
||||
client_params=$(echo "$params" | jq -r '.trt_client_parameters')
|
||||
client_args=$(json2args "$client_params")
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required model_tp_size $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
|
||||
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
|
||||
|
||||
echo "Running test case $test_name"
|
||||
bash ../.buildkite/nightly-benchmarks/scripts/launch-trt-server.sh "$server_params" "$common_params"
|
||||
|
||||
# wait until the server is alive
|
||||
wait_for_server
|
||||
if [ $? -eq 0 ]; then
|
||||
echo ""
|
||||
echo "trt server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "trt failed to start within the timeout period."
|
||||
break
|
||||
fi
|
||||
|
||||
# prepare tokenizer
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
rm -rf /tokenizer_cache
|
||||
mkdir /tokenizer_cache
|
||||
python ../.buildkite/nightly-benchmarks/scripts/download-tokenizer.py \
|
||||
--model "$model" \
|
||||
--cachedir /tokenizer_cache
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
echo "qps was $qps"
|
||||
qps="inf"
|
||||
echo "now qps is $qps"
|
||||
fi
|
||||
|
||||
new_test_name=$test_name"_qps_"$qps
|
||||
|
||||
client_command="python3 benchmark_serving.py \
|
||||
--backend tensorrt-llm \
|
||||
--tokenizer /tokenizer_cache \
|
||||
--model $model \
|
||||
--dataset-name $dataset_name \
|
||||
--dataset-path $dataset_path \
|
||||
--num-prompts $num_prompts \
|
||||
--port $port \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
$client_args"
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
eval "$client_command"
|
||||
|
||||
server_command=""
|
||||
# record the benchmarking commands
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
--arg engine "trt" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu,
|
||||
engine: $engine
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
done
|
||||
|
||||
# clean up
|
||||
kill_gpu_processes
|
||||
rm -rf /root/.cache/huggingface/*
|
||||
done
|
||||
}
|
||||
|
||||
upload_to_buildkite() {
|
||||
# upload the benchmarking results to buildkite
|
||||
|
||||
# if the agent binary is not found, skip uploading the results, exit 0
|
||||
if [ ! -f /workspace/buildkite-agent ]; then
|
||||
echo "buildkite-agent binary not found. Skip uploading the results."
|
||||
return 0
|
||||
fi
|
||||
# /workspace/buildkite-agent annotate --style "success" --context "benchmark-results" --append < $RESULTS_FOLDER/${CURRENT_LLM_SERVING_ENGINE}_nightly_results.md
|
||||
/workspace/buildkite-agent artifact upload "$RESULTS_FOLDER/*"
|
||||
}
|
||||
|
||||
|
||||
main() {
|
||||
|
||||
check_gpus
|
||||
|
||||
|
||||
# enter vllm directory
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
BENCHMARK_ROOT=../.buildkite/nightly-benchmarks/
|
||||
|
||||
# update transformers package, to make sure mixtral tokenizer is available
|
||||
python -m pip install transformers -U
|
||||
|
||||
export CURRENT_LLM_SERVING_ENGINE=trt
|
||||
run_serving_tests $BENCHMARK_ROOT/tests/nightly-tests.json
|
||||
python -m pip install tabulate pandas
|
||||
python $BENCHMARK_ROOT/scripts/summary-nightly-results.py
|
||||
upload_to_buildkite
|
||||
|
||||
}
|
||||
|
||||
main "$@"
|
||||
221
.buildkite/nightly-benchmarks/scripts/run-vllm-nightly.sh
Normal file
221
.buildkite/nightly-benchmarks/scripts/run-vllm-nightly.sh
Normal file
@ -0,0 +1,221 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -o pipefail
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
# kill all processes on GPU.
|
||||
pkill pt_main_thread
|
||||
sleep 10
|
||||
|
||||
# remove vllm config file
|
||||
rm -rf ~/.config/vllm
|
||||
|
||||
# Print the GPU memory usage
|
||||
# so that we know if all GPU processes are killed.
|
||||
gpu_memory_usage=$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i 0)
|
||||
# The memory usage should be 0 MB.
|
||||
echo "GPU 0 Memory Usage: $gpu_memory_usage MB"
|
||||
}
|
||||
|
||||
json2args() {
|
||||
# transforms the JSON string to command line args, and '_' is replaced to '-'
|
||||
# example:
|
||||
# input: { "model": "meta-llama/Llama-2-7b-chat-hf", "tensor_parallel_size": 1 }
|
||||
# output: --model meta-llama/Llama-2-7b-chat-hf --tensor-parallel-size 1
|
||||
local json_string=$1
|
||||
local args=$(
|
||||
echo "$json_string" | jq -r '
|
||||
to_entries |
|
||||
map("--" + (.key | gsub("_"; "-")) + " " + (.value | tostring)) |
|
||||
join(" ")
|
||||
'
|
||||
)
|
||||
echo "$args"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
# wait for vllm server to start
|
||||
# return 1 if vllm server crashes
|
||||
timeout 1200 bash -c '
|
||||
until curl -s localhost:8000/v1/completions > /dev/null; do
|
||||
sleep 1
|
||||
done' && return 0 || return 1
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `benchmark_serving.py`
|
||||
# $1: a json file specifying serving test cases
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# Iterate over serving tests
|
||||
jq -c '.[]' "$serving_test_file" | while read -r params; do
|
||||
# get the test name, and append the GPU type back to it.
|
||||
test_name=$(echo "$params" | jq -r '.test_name')
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# append vllm to the test name
|
||||
test_name=vllm_$test_name
|
||||
|
||||
|
||||
# get common parameters
|
||||
common_params=$(echo "$params" | jq -r '.common_parameters')
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
dataset_name=$(echo "$common_params" | jq -r '.dataset_name')
|
||||
dataset_path=$(echo "$common_params" | jq -r '.dataset_path')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
num_prompts=$(echo "$common_params" | jq -r '.num_prompts')
|
||||
|
||||
# get client and server arguments
|
||||
server_params=$(echo "$params" | jq -r '.vllm_server_parameters')
|
||||
client_params=$(echo "$params" | jq -r '.vllm_client_parameters')
|
||||
server_args=$(json2args "$server_params")
|
||||
client_args=$(json2args "$client_params")
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
if echo "$common_params" | jq -e 'has("fp8")' > /dev/null; then
|
||||
echo "Key 'fp8' exists in common params. Use neuralmagic fp8 model for convenience."
|
||||
model=$(echo "$common_params" | jq -r '.neuralmagic_quantized_model')
|
||||
server_command="python3 \
|
||||
-m vllm.entrypoints.openai.api_server \
|
||||
-tp $tp \
|
||||
--model $model \
|
||||
--port $port \
|
||||
$server_args"
|
||||
else
|
||||
echo "Key 'fp8' does not exist in common params."
|
||||
server_command="python3 \
|
||||
-m vllm.entrypoints.openai.api_server \
|
||||
-tp $tp \
|
||||
--model $model \
|
||||
--port $port \
|
||||
$server_args"
|
||||
fi
|
||||
|
||||
# run the server
|
||||
echo "Running test case $test_name"
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
|
||||
# wait until the server is alive
|
||||
wait_for_server
|
||||
if [ $? -eq 0 ]; then
|
||||
echo ""
|
||||
echo "vllm server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "vllm failed to start within the timeout period."
|
||||
break
|
||||
fi
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
echo "qps was $qps"
|
||||
qps="inf"
|
||||
echo "now qps is $qps"
|
||||
fi
|
||||
|
||||
new_test_name=$test_name"_qps_"$qps
|
||||
|
||||
client_command="python3 benchmark_serving.py \
|
||||
--backend vllm \
|
||||
--model $model \
|
||||
--dataset-name $dataset_name \
|
||||
--dataset-path $dataset_path \
|
||||
--num-prompts $num_prompts \
|
||||
--port $port \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
$client_args"
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
eval "$client_command"
|
||||
|
||||
# record the benchmarking commands
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
--arg engine "vllm" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu,
|
||||
engine: $engine
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
done
|
||||
|
||||
# clean up
|
||||
kill_gpu_processes
|
||||
rm -rf /root/.cache/huggingface/*
|
||||
done
|
||||
}
|
||||
|
||||
|
||||
upload_to_buildkite() {
|
||||
# upload the benchmarking results to buildkite
|
||||
|
||||
# if the agent binary is not found, skip uploading the results, exit 0
|
||||
if [ ! -f /workspace/buildkite-agent ]; then
|
||||
echo "buildkite-agent binary not found. Skip uploading the results."
|
||||
return 0
|
||||
fi
|
||||
# /workspace/buildkite-agent annotate --style "success" --context "benchmark-results" --append < $RESULTS_FOLDER/${CURRENT_LLM_SERVING_ENGINE}_nightly_results.md
|
||||
/workspace/buildkite-agent artifact upload "$RESULTS_FOLDER/*"
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
check_gpus
|
||||
# enter vllm directory
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
BENCHMARK_ROOT=../.buildkite/nightly-benchmarks/
|
||||
|
||||
export CURRENT_LLM_SERVING_ENGINE=vllm
|
||||
run_serving_tests $BENCHMARK_ROOT/tests/nightly-tests.json
|
||||
|
||||
python3 -m pip install tabulate pandas
|
||||
python3 $BENCHMARK_ROOT/scripts/summary-nightly-results.py
|
||||
upload_to_buildkite
|
||||
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@ -0,0 +1,76 @@
|
||||
import datetime
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
import pandas as pd
|
||||
from tabulate import tabulate
|
||||
|
||||
results_folder = Path("results/")
|
||||
|
||||
# serving results and the keys that will be printed into markdown
|
||||
serving_results = []
|
||||
serving_column_mapping = {
|
||||
"test_name": "Test name",
|
||||
"gpu_type": "GPU",
|
||||
"completed": "Successful req.",
|
||||
"request_throughput": "Tput (req/s)",
|
||||
"mean_ttft_ms": "Mean TTFT (ms)",
|
||||
"std_ttft_ms": "Std TTFT (ms)",
|
||||
"mean_itl_ms": "Mean ITL (ms)",
|
||||
"std_itl_ms": "Std ITL (ms)",
|
||||
"input_throughput": "Input Tput (tok/s)",
|
||||
"output_throughput": "Output Tput (tok/s)",
|
||||
"engine": "Engine",
|
||||
}
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
# collect results
|
||||
for test_file in results_folder.glob("*.json"):
|
||||
|
||||
with open(test_file, "r") as f:
|
||||
raw_result = json.loads(f.read())
|
||||
|
||||
# attach the benchmarking command to raw_result
|
||||
with open(test_file.with_suffix(".commands"), "r") as f:
|
||||
command = json.loads(f.read())
|
||||
raw_result.update(command)
|
||||
|
||||
# update the test name of this result
|
||||
raw_result.update({"test_name": test_file.stem})
|
||||
|
||||
# add the result to raw_result
|
||||
serving_results.append(raw_result)
|
||||
continue
|
||||
|
||||
serving_results = pd.DataFrame.from_dict(serving_results)
|
||||
|
||||
if not serving_results.empty:
|
||||
serving_results = serving_results[list(
|
||||
serving_column_mapping.keys())].rename(
|
||||
columns=serving_column_mapping)
|
||||
|
||||
serving_md_table_with_headers = tabulate(serving_results,
|
||||
headers='keys',
|
||||
tablefmt='pipe',
|
||||
showindex=False)
|
||||
# remove the first line of header
|
||||
serving_md_table_lines = serving_md_table_with_headers.split('\n')
|
||||
serving_md_table_without_header = '\n'.join(serving_md_table_lines[2:])
|
||||
|
||||
prefix = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
|
||||
prefix = prefix + "_" + os.environ.get("CURRENT_LLM_SERVING_ENGINE")
|
||||
|
||||
# document benchmarking results in markdown
|
||||
with open(results_folder / f"{prefix}_nightly_results.md", "w") as f:
|
||||
# document results with header.
|
||||
# for those who wants to reproduce our benchmark.
|
||||
f.write(serving_md_table_with_headers)
|
||||
f.write('\n')
|
||||
|
||||
# document benchmarking results in json
|
||||
with open(results_folder / f"{prefix}_nightly_results.json", "w") as f:
|
||||
|
||||
results = serving_results.to_dict(orient='records')
|
||||
f.write(json.dumps(results))
|
||||
116
.buildkite/nightly-benchmarks/tests/nightly-tests.json
Normal file
116
.buildkite/nightly-benchmarks/tests/nightly-tests.json
Normal file
@ -0,0 +1,116 @@
|
||||
[
|
||||
{
|
||||
"test_name": "llama8B_tp1",
|
||||
"qps_list": [4],
|
||||
"common_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-8B",
|
||||
"tp": 1,
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 500,
|
||||
"port": 8000
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "float16",
|
||||
"max_batch_size": 256,
|
||||
"max_input_len": 4096,
|
||||
"max_output_len": 4096,
|
||||
"trt_llm_version": "r24.04"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"disable_log_requests": ""
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "llama70B_tp4",
|
||||
"qps_list": [2],
|
||||
"common_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
|
||||
"tp": 4,
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 500,
|
||||
"port": 8000
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "float16",
|
||||
"max_batch_size": 256,
|
||||
"max_input_len": 4096,
|
||||
"max_output_len": 4096,
|
||||
"trt_llm_version": "r24.04"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"disable_log_requests": ""
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "mixtral8x7B_tp2",
|
||||
"qps_list": [2],
|
||||
"common_parameters": {
|
||||
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
||||
"tp": 2,
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 500,
|
||||
"port": 8000
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "float16",
|
||||
"max_batch_size": 256,
|
||||
"max_input_len": 4096,
|
||||
"max_output_len": 4096,
|
||||
"trt_llm_version": "r24.04"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"disable_log_requests": ""
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
}
|
||||
}
|
||||
]
|
||||
@ -52,6 +52,8 @@ vLLM is fast with:
|
||||
- Quantization: [GPTQ](https://arxiv.org/abs/2210.17323), [AWQ](https://arxiv.org/abs/2306.00978), [SqueezeLLM](https://arxiv.org/abs/2306.07629), FP8 KV Cache
|
||||
- Optimized CUDA kernels
|
||||
|
||||
**Performance benchmark**: We include a [performance benchmark](https://buildkite.com/vllm/performance-benchmark/builds/3924) that compares the performance of vllm against other LLM serving engines ([TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM), [text-generation-inference](https://github.com/huggingface/text-generation-inference) and [lmdeploy](https://github.com/InternLM/lmdeploy)).
|
||||
|
||||
vLLM is flexible and easy to use with:
|
||||
|
||||
- Seamless integration with popular Hugging Face models
|
||||
|
||||
@ -60,12 +60,15 @@ class BenchmarkMetrics:
|
||||
output_throughput: float
|
||||
mean_ttft_ms: float
|
||||
median_ttft_ms: float
|
||||
std_ttft_ms: float
|
||||
p99_ttft_ms: float
|
||||
mean_tpot_ms: float
|
||||
median_tpot_ms: float
|
||||
std_tpot_ms: float
|
||||
p99_tpot_ms: float
|
||||
mean_itl_ms: float
|
||||
median_itl_ms: float
|
||||
std_itl_ms: float
|
||||
p99_itl_ms: float
|
||||
|
||||
|
||||
@ -274,12 +277,15 @@ def calculate_metrics(
|
||||
mean_ttft_ms=np.mean(ttfts or 0) *
|
||||
1000, # ttfts is empty if streaming is not supported by backend
|
||||
median_ttft_ms=np.median(ttfts or 0) * 1000,
|
||||
std_ttft_ms=np.std(ttfts or 0) * 1000,
|
||||
p99_ttft_ms=np.percentile(ttfts or 0, 99) * 1000,
|
||||
mean_tpot_ms=np.mean(tpots or 0) * 1000,
|
||||
median_tpot_ms=np.median(tpots or 0) * 1000,
|
||||
std_tpot_ms=np.std(tpots or 0) * 1000,
|
||||
p99_tpot_ms=np.percentile(tpots or 0, 99) * 1000,
|
||||
mean_itl_ms=np.mean(itls or 0) * 1000,
|
||||
median_itl_ms=np.median(itls or 0) * 1000,
|
||||
std_itl_ms=np.std(itls or 0) * 1000,
|
||||
p99_itl_ms=np.percentile(itls or 0, 99) * 1000,
|
||||
)
|
||||
|
||||
@ -396,12 +402,15 @@ async def benchmark(
|
||||
"output_throughput": metrics.output_throughput,
|
||||
"mean_ttft_ms": metrics.mean_ttft_ms,
|
||||
"median_ttft_ms": metrics.median_ttft_ms,
|
||||
"std_ttft_ms": metrics.std_ttft_ms,
|
||||
"p99_ttft_ms": metrics.p99_ttft_ms,
|
||||
"mean_tpot_ms": metrics.mean_tpot_ms,
|
||||
"median_tpot_ms": metrics.median_tpot_ms,
|
||||
"std_tpot_ms": metrics.std_tpot_ms,
|
||||
"p99_tpot_ms": metrics.p99_tpot_ms,
|
||||
"mean_itl_ms": metrics.mean_itl_ms,
|
||||
"median_itl_ms": metrics.median_itl_ms,
|
||||
"std_itl_ms": metrics.std_itl_ms,
|
||||
"p99_itl_ms": metrics.p99_itl_ms,
|
||||
"input_lens": [output.prompt_len for output in outputs],
|
||||
"output_lens": actual_output_lens,
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user