Add vLLM v0.18.1 source tree with KV transfer abort fix
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
1327
third_party/vllm/.buildkite/performance-benchmarks/scripts/compare-json-results.py
vendored
Normal file
1327
third_party/vllm/.buildkite/performance-benchmarks/scripts/compare-json-results.py
vendored
Normal file
File diff suppressed because it is too large
Load Diff
414
third_party/vllm/.buildkite/performance-benchmarks/scripts/convert-results-json-to-markdown.py
vendored
Normal file
414
third_party/vllm/.buildkite/performance-benchmarks/scripts/convert-results-json-to-markdown.py
vendored
Normal file
@@ -0,0 +1,414 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import shlex
|
||||
from importlib import util
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import pandas as pd
|
||||
import psutil
|
||||
import regex as re
|
||||
from tabulate import tabulate
|
||||
|
||||
# latency results and the keys that will be printed into markdown
|
||||
latency_results = []
|
||||
latency_column_mapping = {
|
||||
"test_name": "Test name",
|
||||
"gpu_type": "GPU",
|
||||
"avg_latency": "Mean latency (ms)",
|
||||
# "P10": "P10 (s)",
|
||||
# "P25": "P25 (s)",
|
||||
"P50": "Median latency (ms)",
|
||||
# "P75": "P75 (s)",
|
||||
# "P90": "P90 (s)",
|
||||
"P99": "P99 latency (ms)",
|
||||
}
|
||||
|
||||
# throughput tests and the keys that will be printed into markdown
|
||||
throughput_results = []
|
||||
throughput_results_column_mapping = {
|
||||
"test_name": "Test name",
|
||||
"gpu_type": "GPU",
|
||||
"num_requests": "# of req.",
|
||||
"total_num_tokens": "Total # of tokens",
|
||||
"elapsed_time": "Elapsed time (s)",
|
||||
"requests_per_second": "Tput (req/s)",
|
||||
"tokens_per_second": "Tput (tok/s)",
|
||||
}
|
||||
|
||||
# serving results and the keys that will be printed into markdown
|
||||
serving_results = []
|
||||
serving_column_mapping = {
|
||||
"test_name": "Test name",
|
||||
"model_id": "Model",
|
||||
"dataset_name": "Dataset Name",
|
||||
"input_len": "Input Len",
|
||||
"output_len": "Output Len",
|
||||
"tp_size": "TP Size",
|
||||
"pp_size": "PP Size",
|
||||
"dtype": "dtype",
|
||||
"gpu_type": "GPU",
|
||||
"completed": "# of req.",
|
||||
"qps": "qps",
|
||||
"max_concurrency": "# of max concurrency.",
|
||||
"request_throughput": "Tput (req/s)",
|
||||
"total_token_throughput": "Total Token Tput (tok/s)",
|
||||
"output_throughput": "Output Tput (tok/s)",
|
||||
# "total_input_tokens": "Total input tokens",
|
||||
# "total_output_tokens": "Total output tokens",
|
||||
"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)",
|
||||
}
|
||||
|
||||
|
||||
def read_markdown(file):
|
||||
if os.path.exists(file):
|
||||
with open(file) as f:
|
||||
return f.read() + "\n"
|
||||
else:
|
||||
return f"{file} not found.\n"
|
||||
|
||||
|
||||
def results_to_json(latency, throughput, serving):
|
||||
return json.dumps(
|
||||
{
|
||||
"latency": latency.to_dict(),
|
||||
"throughput": throughput.to_dict(),
|
||||
"serving": serving.to_dict(),
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def get_size_with_unit(bytes, suffix="B"):
|
||||
"""
|
||||
Scale bytes to its proper format
|
||||
e.g:
|
||||
1253656 => '1.20MB'
|
||||
1253656678 => '1.17GB'
|
||||
"""
|
||||
factor = 1024
|
||||
for unit in ["", "K", "M", "G", "T", "P"]:
|
||||
if bytes < factor:
|
||||
return f"{bytes:.2f}{unit}{suffix}"
|
||||
bytes /= factor
|
||||
|
||||
|
||||
def _coerce(val: str) -> Any:
|
||||
"""Best-effort type coercion from string to Python types."""
|
||||
low = val.lower()
|
||||
if low == "null":
|
||||
return None
|
||||
if low == "true":
|
||||
return True
|
||||
if low == "false":
|
||||
return False
|
||||
# integers
|
||||
if re.fullmatch(r"[+-]?\d+", val):
|
||||
try:
|
||||
return int(val)
|
||||
except ValueError:
|
||||
pass
|
||||
# floats (keep 'inf'/'-inf'/'nan' as strings)
|
||||
if re.fullmatch(r"[+-]?\d*\.\d+", val):
|
||||
try:
|
||||
return float(val)
|
||||
except ValueError:
|
||||
pass
|
||||
return val
|
||||
|
||||
|
||||
def parse_client_command(cmd: str) -> dict[str, Any]:
|
||||
"""Parse the client_command shell string into {executable, script, args}."""
|
||||
toks = shlex.split(cmd)
|
||||
if len(toks) < 2:
|
||||
raise ValueError("client_command must include an executable and a script")
|
||||
executable, script = toks[0], toks[1]
|
||||
args: dict[str, Any] = {}
|
||||
|
||||
i = 2
|
||||
while i < len(toks):
|
||||
t = toks[i]
|
||||
if t.startswith("--"):
|
||||
# --key=value or --key (value) or boolean flag
|
||||
if "=" in t:
|
||||
key, val = t.split("=", 1)
|
||||
if key == "--metadata":
|
||||
md = {}
|
||||
if val:
|
||||
if "=" in val:
|
||||
k, v = val.split("=", 1)
|
||||
md[k] = _coerce(v)
|
||||
else:
|
||||
md[val] = True
|
||||
args[key] = md
|
||||
else:
|
||||
args[key] = _coerce(val)
|
||||
i += 1
|
||||
continue
|
||||
|
||||
key = t
|
||||
|
||||
# Special: consume metadata k=v pairs until next --flag
|
||||
if key == "--metadata":
|
||||
i += 1
|
||||
md = {}
|
||||
while i < len(toks) and not toks[i].startswith("--"):
|
||||
pair = toks[i]
|
||||
if "=" in pair:
|
||||
k, v = pair.split("=", 1)
|
||||
md[k] = _coerce(v)
|
||||
else:
|
||||
md[pair] = True
|
||||
i += 1
|
||||
args[key] = md
|
||||
continue
|
||||
|
||||
# Standard: check if next token is a value (not a flag)
|
||||
if i + 1 < len(toks) and not toks[i + 1].startswith("--"):
|
||||
args[key] = _coerce(toks[i + 1])
|
||||
i += 2
|
||||
else:
|
||||
# lone flag -> True
|
||||
args[key] = True
|
||||
i += 1
|
||||
else:
|
||||
# unexpected positional; skip
|
||||
i += 1
|
||||
|
||||
return {"executable": executable, "script": script, "args": args}
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument(
|
||||
"-r",
|
||||
"--result",
|
||||
type=str,
|
||||
default="results",
|
||||
help="Folder name for benchmark output results.",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
results_folder = Path(args.result)
|
||||
if not results_folder.exists():
|
||||
raise FileNotFoundError(f"results folder does not exist: {results_folder}")
|
||||
# collect results
|
||||
for test_file in results_folder.glob("*.json"):
|
||||
with open(test_file) as f:
|
||||
raw_result = json.loads(f.read())
|
||||
|
||||
if "serving" in str(test_file):
|
||||
# this result is generated via `vllm bench serve` command
|
||||
# attach the benchmarking command to raw_result
|
||||
try:
|
||||
with open(test_file.with_suffix(".commands")) as f:
|
||||
command = json.loads(f.read())
|
||||
except OSError as e:
|
||||
print(e)
|
||||
continue
|
||||
# Parse Server Command Arg
|
||||
out: dict[str, Any] = {
|
||||
"server_command": parse_client_command(command["server_command"])
|
||||
}
|
||||
parse_args = [
|
||||
"--tensor-parallel-size",
|
||||
"--pipeline-parallel-size",
|
||||
"--dtype",
|
||||
]
|
||||
col_mapping = ["tp_size", "pp_size", "dtype"]
|
||||
for index, arg in enumerate(parse_args):
|
||||
if arg in out["server_command"]["args"]:
|
||||
raw_result.update(
|
||||
{col_mapping[index]: out["server_command"]["args"][arg]}
|
||||
)
|
||||
|
||||
# Parse Client Command Arg
|
||||
out: dict[str, Any] = {
|
||||
"client_command": parse_client_command(command["client_command"])
|
||||
}
|
||||
parse_args = [
|
||||
"--dataset-name",
|
||||
"--random-input-len",
|
||||
"--random-output-len",
|
||||
"--request-rate",
|
||||
]
|
||||
col_mapping = ["dataset_name", "input_len", "output_len", "qps"]
|
||||
|
||||
for index, arg in enumerate(parse_args):
|
||||
if arg in out["client_command"]["args"]:
|
||||
raw_result.update(
|
||||
{col_mapping[index]: out["client_command"]["args"][arg]}
|
||||
)
|
||||
# Add Server, Client command
|
||||
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
|
||||
|
||||
elif "latency" in f.name:
|
||||
# this result is generated via `vllm bench latency` command
|
||||
|
||||
# attach the benchmarking command to raw_result
|
||||
try:
|
||||
with open(test_file.with_suffix(".commands")) as f:
|
||||
command = json.loads(f.read())
|
||||
except OSError as e:
|
||||
print(e)
|
||||
continue
|
||||
|
||||
raw_result.update(command)
|
||||
|
||||
# update the test name of this result
|
||||
raw_result.update({"test_name": test_file.stem})
|
||||
|
||||
# get different percentiles
|
||||
for perc in [10, 25, 50, 75, 90, 99]:
|
||||
# Multiply 1000 to convert the time unit from s to ms
|
||||
raw_result.update(
|
||||
{f"P{perc}": 1000 * raw_result["percentiles"][str(perc)]}
|
||||
)
|
||||
raw_result["avg_latency"] = raw_result["avg_latency"] * 1000
|
||||
|
||||
# add the result to raw_result
|
||||
latency_results.append(raw_result)
|
||||
continue
|
||||
|
||||
elif "throughput" in f.name:
|
||||
# this result is generated via `vllm bench throughput` command
|
||||
|
||||
# attach the benchmarking command to raw_result
|
||||
try:
|
||||
with open(test_file.with_suffix(".commands")) as f:
|
||||
command = json.loads(f.read())
|
||||
except OSError as e:
|
||||
print(e)
|
||||
continue
|
||||
|
||||
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
|
||||
throughput_results.append(raw_result)
|
||||
continue
|
||||
|
||||
print(f"Skipping {test_file}")
|
||||
|
||||
latency_results = pd.DataFrame.from_dict(latency_results)
|
||||
serving_results = pd.DataFrame.from_dict(serving_results)
|
||||
throughput_results = pd.DataFrame.from_dict(throughput_results)
|
||||
|
||||
svmem = psutil.virtual_memory()
|
||||
platform_data = {
|
||||
"Physical cores": [psutil.cpu_count(logical=False)],
|
||||
"Total cores": [psutil.cpu_count(logical=True)],
|
||||
"Total Memory": [get_size_with_unit(svmem.total)],
|
||||
}
|
||||
|
||||
if util.find_spec("numa") is not None:
|
||||
from numa import info
|
||||
|
||||
platform_data["Total NUMA nodes"] = [info.get_num_configured_nodes()]
|
||||
|
||||
if util.find_spec("cpuinfo") is not None:
|
||||
from cpuinfo import get_cpu_info
|
||||
|
||||
platform_data["CPU Brand"] = [get_cpu_info()["brand_raw"]]
|
||||
|
||||
platform_results = pd.DataFrame.from_dict(
|
||||
platform_data, orient="index", columns=["Platform Info"]
|
||||
)
|
||||
|
||||
raw_results_json = results_to_json(
|
||||
latency_results, throughput_results, serving_results
|
||||
)
|
||||
|
||||
# remapping the key, for visualization purpose
|
||||
if not latency_results.empty:
|
||||
latency_results = latency_results[list(latency_column_mapping.keys())].rename(
|
||||
columns=latency_column_mapping
|
||||
)
|
||||
if not serving_results.empty:
|
||||
valid_columns = [
|
||||
col for col in serving_column_mapping if col in serving_results.columns
|
||||
]
|
||||
serving_results = serving_results[valid_columns].rename(
|
||||
columns=serving_column_mapping
|
||||
)
|
||||
if not throughput_results.empty:
|
||||
throughput_results = throughput_results[
|
||||
list(throughput_results_column_mapping.keys())
|
||||
].rename(columns=throughput_results_column_mapping)
|
||||
|
||||
processed_results_json = results_to_json(
|
||||
latency_results, throughput_results, serving_results
|
||||
)
|
||||
|
||||
for df in [latency_results, serving_results, throughput_results]:
|
||||
if df.empty:
|
||||
continue
|
||||
|
||||
# Sort all dataframes by their respective "Test name" columns
|
||||
df.sort_values(by="Test name", inplace=True)
|
||||
|
||||
# The GPUs sometimes come in format of "GPUTYPE\nGPUTYPE\n...",
|
||||
# we want to turn it into "8xGPUTYPE"
|
||||
df["GPU"] = df["GPU"].apply(
|
||||
lambda x: "{}x{}".format(len(x.split("\n")), x.split("\n")[0])
|
||||
)
|
||||
|
||||
# get markdown tables
|
||||
latency_md_table = tabulate(
|
||||
latency_results, headers="keys", tablefmt="pipe", showindex=False
|
||||
)
|
||||
serving_md_table = tabulate(
|
||||
serving_results, headers="keys", tablefmt="pipe", showindex=False
|
||||
)
|
||||
throughput_md_table = tabulate(
|
||||
throughput_results, headers="keys", tablefmt="pipe", showindex=False
|
||||
)
|
||||
platform_md_table = tabulate(
|
||||
platform_results, headers="keys", tablefmt="pipe", showindex=True
|
||||
)
|
||||
|
||||
# document the result
|
||||
md_file = "benchmark_results.md"
|
||||
json_file = "benchmark_results.json"
|
||||
with open(results_folder / md_file, "w") as f:
|
||||
results = read_markdown(
|
||||
"../.buildkite/performance-benchmarks/"
|
||||
"performance-benchmarks-descriptions.md"
|
||||
)
|
||||
results = results.format(
|
||||
latency_tests_markdown_table=latency_md_table,
|
||||
throughput_tests_markdown_table=throughput_md_table,
|
||||
serving_tests_markdown_table=serving_md_table,
|
||||
platform_markdown_table=platform_md_table,
|
||||
benchmarking_results_in_json_string=processed_results_json,
|
||||
)
|
||||
f.write(results)
|
||||
|
||||
# document benchmarking results in json
|
||||
with open(results_folder / json_file, "w") as f:
|
||||
results = (
|
||||
latency_results.to_dict(orient="records")
|
||||
+ throughput_results.to_dict(orient="records")
|
||||
+ serving_results.to_dict(orient="records")
|
||||
)
|
||||
f.write(json.dumps(results))
|
||||
224
third_party/vllm/.buildkite/performance-benchmarks/scripts/launch-server.sh
vendored
Normal file
224
third_party/vllm/.buildkite/performance-benchmarks/scripts/launch-server.sh
vendored
Normal file
@@ -0,0 +1,224 @@
|
||||
#!/bin/bash
|
||||
|
||||
# Currently FP8 benchmark is NOT enabled.
|
||||
|
||||
set -x
|
||||
server_params=$1
|
||||
common_params=$2
|
||||
|
||||
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"
|
||||
}
|
||||
|
||||
launch_trt_server() {
|
||||
|
||||
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 "$server_params" | jq -r '.max_input_len')
|
||||
max_seq_len=$(echo "$server_params" | jq -r '.max_seq_len')
|
||||
max_num_tokens=$(echo "$server_params" | jq -r '.max_num_tokens')
|
||||
trt_llm_version=$(echo "$server_params" | jq -r '.trt_llm_version')
|
||||
|
||||
# create model caching directory
|
||||
cd ~
|
||||
rm -rf models
|
||||
mkdir -p models
|
||||
cd models
|
||||
models_dir=$(pwd)
|
||||
trt_model_path=${models_dir}/${model_name}-trt-ckpt
|
||||
trt_engine_path=${models_dir}/${model_name}-trt-engine
|
||||
|
||||
# clone tensorrt backend
|
||||
cd /
|
||||
rm -rf tensorrtllm_backend
|
||||
git clone https://github.com/triton-inference-server/tensorrtllm_backend.git
|
||||
git lfs install
|
||||
cd tensorrtllm_backend
|
||||
git checkout "$trt_llm_version"
|
||||
git submodule update --init --recursive
|
||||
|
||||
# build trtllm engine
|
||||
cd /tensorrtllm_backend
|
||||
cd "./tensorrt_llm/examples/${model_type}"
|
||||
python3 convert_checkpoint.py \
|
||||
--model_dir "${model_path}" \
|
||||
--dtype "${model_dtype}" \
|
||||
--tp_size "${model_tp_size}" \
|
||||
--output_dir "${trt_model_path}"
|
||||
trtllm-build \
|
||||
--checkpoint_dir "${trt_model_path}" \
|
||||
--use_fused_mlp \
|
||||
--reduce_fusion disable \
|
||||
--workers 8 \
|
||||
--gpt_attention_plugin "${model_dtype}" \
|
||||
--gemm_plugin "${model_dtype}" \
|
||||
--tp_size "${model_tp_size}" \
|
||||
--max_batch_size "${max_batch_size}" \
|
||||
--max_input_len "${max_input_len}" \
|
||||
--max_seq_len "${max_seq_len}" \
|
||||
--max_num_tokens "${max_num_tokens}" \
|
||||
--output_dir "${trt_engine_path}"
|
||||
|
||||
# handle triton protobuf files and launch triton server
|
||||
cd /tensorrtllm_backend
|
||||
mkdir triton_model_repo
|
||||
cp -r all_models/inflight_batcher_llm/* triton_model_repo/
|
||||
cd triton_model_repo
|
||||
rm -rf ./tensorrt_llm/1/*
|
||||
cp -r "${trt_engine_path}"/* ./tensorrt_llm/1
|
||||
python3 ../tools/fill_template.py -i tensorrt_llm/config.pbtxt triton_backend:tensorrtllm,engine_dir:/tensorrtllm_backend/triton_model_repo/tensorrt_llm/1,decoupled_mode:true,batching_strategy:inflight_fused_batching,batch_scheduler_policy:guaranteed_no_evict,exclude_input_in_output:true,triton_max_batch_size:2048,max_queue_delay_microseconds:0,max_beam_width:1,max_queue_size:2048,enable_kv_cache_reuse:false
|
||||
python3 ../tools/fill_template.py -i preprocessing/config.pbtxt "triton_max_batch_size:2048,tokenizer_dir:$model_path,preprocessing_instance_count:5"
|
||||
python3 ../tools/fill_template.py -i postprocessing/config.pbtxt "triton_max_batch_size:2048,tokenizer_dir:$model_path,postprocessing_instance_count:5,skip_special_tokens:false"
|
||||
python3 ../tools/fill_template.py -i ensemble/config.pbtxt triton_max_batch_size:"$max_batch_size"
|
||||
python3 ../tools/fill_template.py -i tensorrt_llm_bls/config.pbtxt "triton_max_batch_size:$max_batch_size,decoupled_mode:true,accumulate_tokens:False,bls_instance_count:1"
|
||||
cd /tensorrtllm_backend
|
||||
python3 scripts/launch_triton_server.py \
|
||||
--world_size="${model_tp_size}" \
|
||||
--model_repo=/tensorrtllm_backend/triton_model_repo &
|
||||
|
||||
}
|
||||
|
||||
launch_tgi_server() {
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
server_args=$(json2args "$server_params")
|
||||
|
||||
if echo "$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
|
||||
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
|
||||
}
|
||||
|
||||
launch_lmdeploy_server() {
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
server_args=$(json2args "$server_params")
|
||||
|
||||
server_command="lmdeploy serve api_server $model \
|
||||
--tp $tp \
|
||||
--server-port $port \
|
||||
$server_args"
|
||||
|
||||
# run the server
|
||||
echo "Server command: $server_command"
|
||||
bash -c "$server_command" &
|
||||
}
|
||||
|
||||
launch_sglang_server() {
|
||||
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
server_args=$(json2args "$server_params")
|
||||
|
||||
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 sglang.launch_server \
|
||||
--tp $tp \
|
||||
--model-path $model \
|
||||
--port $port \
|
||||
$server_args"
|
||||
else
|
||||
echo "Key 'fp8' does not exist in common params."
|
||||
server_command="python3 \
|
||||
-m sglang.launch_server \
|
||||
--tp $tp \
|
||||
--model-path $model \
|
||||
--port $port \
|
||||
$server_args"
|
||||
fi
|
||||
|
||||
# run the server
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
}
|
||||
|
||||
launch_vllm_server() {
|
||||
|
||||
export VLLM_HOST_IP=$(hostname -I | awk '{print $1}')
|
||||
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
server_args=$(json2args "$server_params")
|
||||
|
||||
if echo "$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="vllm serve $model \
|
||||
-tp $tp \
|
||||
--port $port \
|
||||
$server_args"
|
||||
else
|
||||
echo "Key 'fp8' does not exist in common params."
|
||||
server_command="vllm serve $model \
|
||||
-tp $tp \
|
||||
--port $port \
|
||||
$server_args"
|
||||
fi
|
||||
|
||||
# run the server
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
if [[ "$CURRENT_LLM_SERVING_ENGINE" == "trt" ]]; then
|
||||
launch_trt_server
|
||||
fi
|
||||
|
||||
if [[ "$CURRENT_LLM_SERVING_ENGINE" == "tgi" ]]; then
|
||||
launch_tgi_server
|
||||
fi
|
||||
|
||||
if [[ "$CURRENT_LLM_SERVING_ENGINE" == "lmdeploy" ]]; then
|
||||
launch_lmdeploy_server
|
||||
fi
|
||||
|
||||
if [[ "$CURRENT_LLM_SERVING_ENGINE" == "sglang" ]]; then
|
||||
launch_sglang_server
|
||||
fi
|
||||
|
||||
if [[ "$CURRENT_LLM_SERVING_ENGINE" == *"vllm"* ]]; then
|
||||
launch_vllm_server
|
||||
fi
|
||||
}
|
||||
|
||||
main
|
||||
896
third_party/vllm/.buildkite/performance-benchmarks/scripts/run-performance-benchmarks.sh
vendored
Normal file
896
third_party/vllm/.buildkite/performance-benchmarks/scripts/run-performance-benchmarks.sh
vendored
Normal file
@@ -0,0 +1,896 @@
|
||||
#!/bin/bash
|
||||
# This script assumes that we are already inside the vllm/ directory
|
||||
# Benchmarking results will be available inside vllm/benchmarks/results/
|
||||
|
||||
# Do not set -e, as the mixtral 8x22B model tends to crash occasionally
|
||||
# and we still want to see other benchmarking results even when mixtral crashes.
|
||||
set -x
|
||||
set -o pipefail
|
||||
|
||||
# Environment-driven debug controls (like ON_CPU=1)
|
||||
DRY_RUN="${DRY_RUN:-0}"
|
||||
MODEL_FILTER="${MODEL_FILTER:-}"
|
||||
DTYPE_FILTER="${DTYPE_FILTER:-}"
|
||||
|
||||
# Adaptive search controls
|
||||
ENABLE_ADAPTIVE_CONCURRENCY="${ENABLE_ADAPTIVE_CONCURRENCY:-0}"
|
||||
SLA_TTFT_MS="${SLA_TTFT_MS:-3000}"
|
||||
SLA_TPOT_MS="${SLA_TPOT_MS:-100}"
|
||||
ADAPTIVE_MAX_PROBES="${ADAPTIVE_MAX_PROBES:-8}"
|
||||
ADAPTIVE_MAX_CONCURRENCY="${ADAPTIVE_MAX_CONCURRENCY:-1024}"
|
||||
|
||||
check_gpus() {
|
||||
if command -v nvidia-smi; then
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | grep -c . || true)
|
||||
elif command -v amd-smi; then
|
||||
declare -g gpu_count=$(amd-smi list | grep -c 'GPU' || true)
|
||||
elif command -v hl-smi; then
|
||||
declare -g gpu_count=$(hl-smi --list | grep -ci "Module ID" || true)
|
||||
fi
|
||||
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
declare -g arch_suffix=''
|
||||
|
||||
if command -v nvidia-smi; then
|
||||
declare -g gpu_type=$(nvidia-smi --query-gpu=name --format=csv,noheader | awk '{print $2}')
|
||||
elif command -v amd-smi; then
|
||||
declare -g gpu_type=$(amd-smi static -g 0 -a | grep 'MARKET_NAME' | awk '{print $2}')
|
||||
elif command -v hl-smi; then
|
||||
declare -g gpu_type=$(hl-smi -q | grep "Product Name" | head -n 1 | awk -F ':' '{print $2}' | sed 's/^ *//')
|
||||
arch_suffix='-hpu'
|
||||
fi
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
check_cpus() {
|
||||
# check the number of CPUs and NUMA Node and GPU type.
|
||||
declare -g numa_count=$(lscpu | grep "NUMA node(s):" | awk '{print $3}')
|
||||
if [[ $numa_count -gt 0 ]]; then
|
||||
echo "NUMA found."
|
||||
echo "$numa_count"
|
||||
else
|
||||
echo "Need at least 1 NUMA to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
if [[ "$(uname -m)" == "aarch64" ]] || [[ "$(uname -m)" == "arm64" ]]; then
|
||||
declare -g gpu_type="arm64-cpu"
|
||||
else
|
||||
declare -g gpu_type="cpu"
|
||||
fi
|
||||
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 [[ ! "$HF_TOKEN" =~ ^hf_ ]]; then
|
||||
echo "Error: HF_TOKEN does not start with 'hf_'."
|
||||
exit 1
|
||||
else
|
||||
echo "HF_TOKEN is set and valid."
|
||||
fi
|
||||
}
|
||||
|
||||
ensure_sharegpt_downloaded() {
|
||||
local FILE=ShareGPT_V3_unfiltered_cleaned_split.json
|
||||
if [ ! -f "$FILE" ]; then
|
||||
wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/$FILE
|
||||
else
|
||||
echo "$FILE already exists."
|
||||
fi
|
||||
}
|
||||
|
||||
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"
|
||||
}
|
||||
|
||||
json2envs() {
|
||||
# transforms the JSON string to environment variables.
|
||||
# example:
|
||||
# input: { "VLLM_CPU_KVCACHE_SPACE": 5 }
|
||||
# output: VLLM_CPU_KVCACHE_SPACE=5
|
||||
local json_string=$1
|
||||
local args=$(
|
||||
echo "$json_string" | jq -r '
|
||||
to_entries |
|
||||
map((.key ) + "=" + (.value | tostring)) |
|
||||
join(" ")
|
||||
'
|
||||
)
|
||||
echo "$args"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
local timeout_val="1200"
|
||||
timeout "$timeout_val" bash -c '
|
||||
until curl -sf http://localhost:8000/v1/models >/dev/null; do
|
||||
sleep 1
|
||||
done
|
||||
'
|
||||
}
|
||||
|
||||
kill_processes_launched_by_current_bash() {
|
||||
# Kill all python processes launched from current bash script
|
||||
current_shell_pid=$$
|
||||
processes=$(ps -eo pid,ppid,command | awk -v ppid="$current_shell_pid" -v proc="$1" '$2 == ppid && $3 ~ proc {print $1}')
|
||||
if [ -n "$processes" ]; then
|
||||
echo "Killing the following processes matching '$1':"
|
||||
echo "$processes"
|
||||
echo "$processes" | xargs kill -9
|
||||
else
|
||||
echo "No processes found matching '$1'."
|
||||
fi
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
|
||||
ps -aux
|
||||
lsof -t -i:8000 | xargs -r kill -9
|
||||
pgrep python3 | xargs -r kill -9
|
||||
# vLLM now names the process with VLLM prefix after https://github.com/vllm-project/vllm/pull/21445
|
||||
pgrep VLLM | xargs -r kill -9
|
||||
|
||||
# wait until GPU memory usage smaller than 1GB
|
||||
if command -v nvidia-smi; then
|
||||
while [ "$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -n 1)" -ge 1000 ]; do
|
||||
sleep 1
|
||||
done
|
||||
elif command -v amd-smi; then
|
||||
while [ "$(amd-smi metric -g 0 | grep 'USED_VRAM' | awk '{print $2}')" -ge 1000 ]; do
|
||||
sleep 1
|
||||
done
|
||||
elif command -v hl-smi; then
|
||||
while [ "$(hl-smi -q | grep "Used" | head -n 1 | awk '{print $3}')" -ge 1000 ]; do
|
||||
sleep 1
|
||||
done
|
||||
fi
|
||||
|
||||
# remove vllm config file
|
||||
rm -rf ~/.config/vllm
|
||||
|
||||
}
|
||||
|
||||
upload_to_buildkite() {
|
||||
# upload the benchmarking results to buildkite
|
||||
|
||||
# if the agent binary is not found, skip uploading the results, exit 0
|
||||
# Check if buildkite-agent is available in the PATH or at /workspace/buildkite-agent
|
||||
if command -v buildkite-agent >/dev/null 2>&1; then
|
||||
BUILDKITE_AGENT_COMMAND="buildkite-agent"
|
||||
elif [ -f /workspace/buildkite-agent ]; then
|
||||
BUILDKITE_AGENT_COMMAND="/workspace/buildkite-agent"
|
||||
else
|
||||
echo "buildkite-agent binary not found. Skip uploading the results."
|
||||
return 0
|
||||
fi
|
||||
|
||||
# Use the determined command to annotate and upload artifacts
|
||||
$BUILDKITE_AGENT_COMMAND annotate --style "info" --context "$BUILDKITE_LABEL-benchmark-results" < "$RESULTS_FOLDER/benchmark_results.md"
|
||||
$BUILDKITE_AGENT_COMMAND artifact upload "$RESULTS_FOLDER/*"
|
||||
}
|
||||
|
||||
# -------------------------------
|
||||
# Adaptive concurrency helpers
|
||||
# -------------------------------
|
||||
result_json_path_for_serving() {
|
||||
local test_name=$1
|
||||
local qps=$2
|
||||
local max_concurrency=$3
|
||||
echo "$RESULTS_FOLDER/${test_name}_qps_${qps}_concurrency_${max_concurrency}.json"
|
||||
}
|
||||
|
||||
extract_metric_ms() {
|
||||
local metric_name=$1
|
||||
local json_file=$2
|
||||
|
||||
[[ -f "$json_file" ]] || return 0
|
||||
|
||||
if [[ "$metric_name" == "ttft" ]]; then
|
||||
jq -r '
|
||||
[
|
||||
.ttft_ms.p99?,
|
||||
.metrics.ttft_ms.p99?,
|
||||
.ttft.p99?,
|
||||
.metrics.ttft.p99?,
|
||||
.p99_ttft_ms?,
|
||||
.ttft_ms.mean?,
|
||||
.metrics.ttft_ms.mean?,
|
||||
.ttft.mean?,
|
||||
.metrics.ttft.mean?,
|
||||
.mean_ttft_ms?
|
||||
] | map(select(. != null)) | .[0] // empty
|
||||
' "$json_file"
|
||||
else
|
||||
jq -r '
|
||||
[
|
||||
.tpot_ms.p99?,
|
||||
.metrics.tpot_ms.p99?,
|
||||
.tpot.p99?,
|
||||
.metrics.tpot.p99?,
|
||||
.p99_tpot_ms?,
|
||||
.itl_ms.p99?,
|
||||
.metrics.itl_ms.p99?,
|
||||
.inter_token_latency_ms.p99?,
|
||||
.tpot_ms.mean?,
|
||||
.metrics.tpot_ms.mean?,
|
||||
.tpot.mean?,
|
||||
.metrics.tpot.mean?,
|
||||
.itl_ms.mean?,
|
||||
.metrics.itl_ms.mean?,
|
||||
.mean_tpot_ms?,
|
||||
.mean_itl_ms?
|
||||
] | map(select(. != null)) | .[0] // empty
|
||||
' "$json_file"
|
||||
fi
|
||||
}
|
||||
|
||||
evaluate_sla_from_json() {
|
||||
local json_file=$1
|
||||
local ttft
|
||||
local tpot
|
||||
local pass
|
||||
|
||||
[[ -f "$json_file" ]] || return 2
|
||||
|
||||
ttft=$(extract_metric_ms ttft "$json_file")
|
||||
tpot=$(extract_metric_ms tpot "$json_file")
|
||||
|
||||
[[ -n "$ttft" && -n "$tpot" ]] || return 2
|
||||
|
||||
pass=$(jq -n \
|
||||
--argjson ttft "$ttft" \
|
||||
--argjson tpot "$tpot" \
|
||||
--argjson sla_ttft "$SLA_TTFT_MS" \
|
||||
--argjson sla_tpot "$SLA_TPOT_MS" \
|
||||
'($ttft <= $sla_ttft) and ($tpot <= $sla_tpot)')
|
||||
|
||||
[[ "$pass" == "true" ]]
|
||||
}
|
||||
|
||||
write_adaptive_summary_json() {
|
||||
local summary_file=$1
|
||||
local test_name=$2
|
||||
local qps=$3
|
||||
local static_last_pass=$4
|
||||
local static_first_fail=$5
|
||||
local final_last_pass=$6
|
||||
local final_first_fail=$7
|
||||
|
||||
jq -n \
|
||||
--arg test_name "$test_name" \
|
||||
--arg qps "$qps" \
|
||||
--argjson sla_ttft "$SLA_TTFT_MS" \
|
||||
--argjson sla_tpot "$SLA_TPOT_MS" \
|
||||
--arg static_last_pass "${static_last_pass:-}" \
|
||||
--arg static_first_fail "${static_first_fail:-}" \
|
||||
--arg final_last_pass "${final_last_pass:-}" \
|
||||
--arg final_first_fail "${final_first_fail:-}" \
|
||||
'{
|
||||
test_name: $test_name,
|
||||
qps: $qps,
|
||||
sla_ttft_ms: $sla_ttft,
|
||||
sla_tpot_ms: $sla_tpot,
|
||||
static_last_pass: (if $static_last_pass == "" then null else ($static_last_pass | tonumber) end),
|
||||
static_first_fail: (if $static_first_fail == "" then null else ($static_first_fail | tonumber) end),
|
||||
final_last_pass: (if $final_last_pass == "" then null else ($final_last_pass | tonumber) end),
|
||||
final_first_fail: (if $final_first_fail == "" then null else ($final_first_fail | tonumber) end)
|
||||
}' > "$summary_file"
|
||||
}
|
||||
|
||||
run_single_serving_probe() {
|
||||
local test_name=$1
|
||||
local qps=$2
|
||||
local max_concurrency=$3
|
||||
local tp=$4
|
||||
local compilation_config_mode=$5
|
||||
local optimization_level=$6
|
||||
local client_args_effective=$7
|
||||
local client_remote_args=$8
|
||||
local server_command=$9
|
||||
|
||||
local new_test_name="${test_name}_qps_${qps}_concurrency_${max_concurrency}"
|
||||
local result_json
|
||||
local num_prompts_arg=""
|
||||
local client_command
|
||||
|
||||
result_json=$(result_json_path_for_serving "$test_name" "$qps" "$max_concurrency")
|
||||
|
||||
if [[ -f "$result_json" ]]; then
|
||||
evaluate_sla_from_json "$result_json"
|
||||
return $?
|
||||
fi
|
||||
|
||||
if [[ -n "${PROMPTS_PER_CONCURRENCY}" ]]; then
|
||||
num_prompts=$(( max_concurrency * PROMPTS_PER_CONCURRENCY ))
|
||||
if (( num_prompts < MIN_NUM_PROMPTS )); then num_prompts=$MIN_NUM_PROMPTS; fi
|
||||
if (( num_prompts > MAX_NUM_PROMPTS )); then num_prompts=$MAX_NUM_PROMPTS; fi
|
||||
num_prompts_arg="--num-prompts $num_prompts"
|
||||
fi
|
||||
|
||||
client_command="vllm bench serve \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
--max-concurrency $max_concurrency \
|
||||
$num_prompts_arg \
|
||||
--metadata tensor_parallel_size=$tp compilation_config.mode=$compilation_config_mode optimization_level=$optimization_level adaptive_search=1 \
|
||||
$client_args_effective $client_remote_args "
|
||||
|
||||
echo "Adaptive probe: $client_command"
|
||||
|
||||
if [[ "${DRY_RUN:-0}" != "1" ]]; then
|
||||
bash -c "$client_command"
|
||||
fi
|
||||
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu,
|
||||
adaptive_search: true
|
||||
}')
|
||||
echo "$jq_output" > "$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
evaluate_sla_from_json "$result_json"
|
||||
}
|
||||
|
||||
adaptive_refine_from_static_results() {
|
||||
local test_name=$1
|
||||
local qps=$2
|
||||
local max_concurrency_list_raw=$3
|
||||
local tp=$4
|
||||
local compilation_config_mode=$5
|
||||
local optimization_level=$6
|
||||
local client_args_effective=$7
|
||||
local client_remote_args=$8
|
||||
local server_command=$9
|
||||
|
||||
local sorted_points
|
||||
local point
|
||||
local rc
|
||||
local static_last_pass=""
|
||||
local static_first_fail=""
|
||||
local largest_static=""
|
||||
local step_hint=1
|
||||
local previous_point=""
|
||||
local low
|
||||
local high
|
||||
local mid
|
||||
local probes=0
|
||||
local summary_file="$RESULTS_FOLDER/${test_name}_qps_${qps}_sla_summary.json"
|
||||
|
||||
[[ "${ENABLE_ADAPTIVE_CONCURRENCY}" == "1" ]] || return 0
|
||||
[[ "${DRY_RUN:-0}" != "1" ]] || return 0
|
||||
|
||||
sorted_points=$(for point in $max_concurrency_list_raw; do printf '%s\n' "$point"; done | tr -d "'" | awk '/^[0-9]+$/' | sort -n | uniq)
|
||||
[[ -n "$sorted_points" ]] || return 0
|
||||
|
||||
while read -r point; do
|
||||
[[ -z "$point" ]] && continue
|
||||
largest_static="$point"
|
||||
evaluate_sla_from_json "$(result_json_path_for_serving "$test_name" "$qps" "$point")"
|
||||
rc=$?
|
||||
if (( rc == 0 )); then
|
||||
static_last_pass="$point"
|
||||
elif (( rc == 1 )); then
|
||||
if [[ -n "$static_last_pass" ]]; then
|
||||
static_first_fail="$point"
|
||||
break
|
||||
fi
|
||||
fi
|
||||
|
||||
if [[ -n "$previous_point" ]]; then
|
||||
step_hint=$(( point - previous_point ))
|
||||
if (( step_hint < 1 )); then step_hint=1; fi
|
||||
fi
|
||||
previous_point="$point"
|
||||
done <<< "$sorted_points"
|
||||
|
||||
if [[ -z "$static_last_pass" ]]; then
|
||||
write_adaptive_summary_json "$summary_file" "$test_name" "$qps" "" "$static_first_fail" "" "$static_first_fail"
|
||||
return 0
|
||||
fi
|
||||
|
||||
if [[ -n "$static_first_fail" ]]; then
|
||||
low=$static_last_pass
|
||||
high=$static_first_fail
|
||||
while (( low + 1 < high )) && (( probes < ADAPTIVE_MAX_PROBES )); do
|
||||
mid=$(( (low + high) / 2 ))
|
||||
probes=$(( probes + 1 ))
|
||||
run_single_serving_probe \
|
||||
"$test_name" "$qps" "$mid" "$tp" \
|
||||
"$compilation_config_mode" "$optimization_level" \
|
||||
"$client_args_effective" "$client_remote_args" "$server_command"
|
||||
rc=$?
|
||||
if (( rc == 0 )); then
|
||||
low=$mid
|
||||
elif (( rc == 1 )); then
|
||||
high=$mid
|
||||
else
|
||||
break
|
||||
fi
|
||||
done
|
||||
write_adaptive_summary_json "$summary_file" "$test_name" "$qps" "$static_last_pass" "$static_first_fail" "$low" "$high"
|
||||
return 0
|
||||
fi
|
||||
|
||||
low=$largest_static
|
||||
high=""
|
||||
while (( probes < ADAPTIVE_MAX_PROBES )); do
|
||||
point=$(( low + step_hint ))
|
||||
if (( point > ADAPTIVE_MAX_CONCURRENCY )); then
|
||||
point=$ADAPTIVE_MAX_CONCURRENCY
|
||||
fi
|
||||
(( point > low )) || break
|
||||
probes=$(( probes + 1 ))
|
||||
run_single_serving_probe \
|
||||
"$test_name" "$qps" "$point" "$tp" \
|
||||
"$compilation_config_mode" "$optimization_level" \
|
||||
"$client_args_effective" "$client_remote_args" "$server_command"
|
||||
rc=$?
|
||||
if (( rc == 0 )); then
|
||||
low=$point
|
||||
(( point == ADAPTIVE_MAX_CONCURRENCY )) && break
|
||||
step_hint=$(( step_hint * 2 ))
|
||||
if (( step_hint < 1 )); then step_hint=1; fi
|
||||
elif (( rc == 1 )); then
|
||||
high=$point
|
||||
break
|
||||
else
|
||||
break
|
||||
fi
|
||||
done
|
||||
|
||||
if [[ -n "$high" ]]; then
|
||||
while (( low + 1 < high )) && (( probes < ADAPTIVE_MAX_PROBES )); do
|
||||
mid=$(( (low + high) / 2 ))
|
||||
probes=$(( probes + 1 ))
|
||||
run_single_serving_probe \
|
||||
"$test_name" "$qps" "$mid" "$tp" \
|
||||
"$compilation_config_mode" "$optimization_level" \
|
||||
"$client_args_effective" "$client_remote_args" "$server_command"
|
||||
rc=$?
|
||||
if (( rc == 0 )); then
|
||||
low=$mid
|
||||
elif (( rc == 1 )); then
|
||||
high=$mid
|
||||
else
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
write_adaptive_summary_json "$summary_file" "$test_name" "$qps" "$static_last_pass" "" "$low" "$high"
|
||||
}
|
||||
|
||||
run_benchmark_tests() {
|
||||
# run benchmark tests using `vllm bench <test_type>` command
|
||||
# $1: test type (latency or throughput)
|
||||
# $2: a json file specifying test cases
|
||||
|
||||
local test_type=$1
|
||||
local test_file=$2
|
||||
|
||||
# Iterate over tests
|
||||
jq -c '.[]' "$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 [[ ! "$test_name" =~ ^${test_type}_ ]]; then
|
||||
echo "In ${test_type}-test.json, test_name must start with \"${test_type}_\"."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# 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 $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# get arguments
|
||||
bench_params=$(echo "$params" | jq -r '.parameters')
|
||||
bench_args=$(json2args "$bench_params")
|
||||
bench_environment_variables=$(echo "$params" | jq -r '.environment_variables')
|
||||
bench_envs=$(json2envs "$bench_environment_variables")
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
tp=$(echo "$bench_params" | jq -r '.tensor_parallel_size')
|
||||
if [[ "$ON_CPU" == "1" ]]; then
|
||||
pp=$(echo "$bench_params" | jq -r '.pipeline_parallel_size // 1')
|
||||
world_size=$(($tp*$pp))
|
||||
if [[ $numa_count -lt $world_size && -z "${REMOTE_HOST}" ]]; then
|
||||
echo "Required world-size $world_size but only $numa_count NUMA nodes found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
else
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
fi
|
||||
|
||||
bench_command=" $bench_envs vllm bench $test_type \
|
||||
--output-json $RESULTS_FOLDER/${test_name}.json \
|
||||
$bench_args"
|
||||
|
||||
echo "Running test case $test_name"
|
||||
echo "${test_type^} command: $bench_command"
|
||||
|
||||
# recording benchmarking command and GPU command
|
||||
jq_output=$(jq -n \
|
||||
--arg command "$bench_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
--arg test_type "$test_type" \
|
||||
'{
|
||||
($test_type + "_command"): $command,
|
||||
gpu_type: $gpu
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/$test_name.commands"
|
||||
|
||||
# run the benchmark
|
||||
eval "$bench_command"
|
||||
|
||||
kill_gpu_processes
|
||||
|
||||
done
|
||||
}
|
||||
|
||||
run_latency_tests() { run_benchmark_tests "latency" "$1"; }
|
||||
run_startup_tests() { run_benchmark_tests "startup" "$1"; }
|
||||
run_throughput_tests() { run_benchmark_tests "throughput" "$1"; }
|
||||
|
||||
merge_serving_tests_stream() {
|
||||
# Emit merged serving test objects, optionally filtered by MODEL_FILTER/DTYPE_FILTER in DRY_RUN mode.
|
||||
# This helper does NOT modify JSON; it only filters the stream in dry-run mode.
|
||||
local serving_test_file="$1"
|
||||
# shellcheck disable=SC2016
|
||||
local merged='
|
||||
if type == "array" then
|
||||
# Plain format: test cases array
|
||||
.[]
|
||||
elif (type == "object" and has("tests")) then
|
||||
# merge the default parameters into each test cases
|
||||
. as $root
|
||||
| ($root.defaults // {}) as $d
|
||||
| ($root.tests // [])[]
|
||||
# default qps / max_concurrency from defaults if missing
|
||||
| .qps_list = (.qps_list // $d.qps_list)
|
||||
| .max_concurrency_list = (.max_concurrency_list // $d.max_concurrency_list)
|
||||
# merge envs / params: test overrides defaults
|
||||
| .server_environment_variables =
|
||||
(($d.server_environment_variables // {}) + (.server_environment_variables // {}))
|
||||
| .server_parameters =
|
||||
(($d.server_parameters // {}) + (.server_parameters // {}))
|
||||
| .client_parameters =
|
||||
(($d.client_parameters // {}) + (.client_parameters // {}))
|
||||
else
|
||||
error("Unsupported serving test file format: must be array or object with .tests")
|
||||
end
|
||||
'
|
||||
|
||||
jq -c "$merged" "$serving_test_file" | \
|
||||
if [[ "${DRY_RUN:-0}" == "1" && ( "${MODEL_FILTER}${DTYPE_FILTER}" != "" ) ]]; then
|
||||
jq -c --arg model "$MODEL_FILTER" --arg dtype "$DTYPE_FILTER" '
|
||||
select((($model|length)==0)
|
||||
or ((.server_parameters.model // "") == $model)
|
||||
or ((.client_parameters.model // "") == $model))
|
||||
| select((($dtype|length)==0) or ((.server_parameters.dtype // "") == $dtype))
|
||||
'
|
||||
else
|
||||
cat
|
||||
fi
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `vllm bench serve` command
|
||||
# $1: a json file specifying serving test cases
|
||||
#
|
||||
# Supported JSON formats:
|
||||
# 1) Plain format: top-level array
|
||||
# [ { "test_name": "...", "server_parameters": {...}, ... }, ... ]
|
||||
#
|
||||
# 2) Default parameters field + plain format tests
|
||||
# {
|
||||
# "defaults": { ... },
|
||||
# "tests": [ { "test_name": "...", "server_parameters": {...}, ... }, ... ]
|
||||
# }
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# In dry-run mode, if filters are provided but no tests match, fail fast.
|
||||
if [[ "${DRY_RUN:-0}" == "1" && ( "${MODEL_FILTER}${DTYPE_FILTER}" != "" ) ]]; then
|
||||
local count
|
||||
count=$(merge_serving_tests_stream "$serving_test_file" | wc -l | tr -d ' ')
|
||||
if [[ "$count" -eq 0 ]]; then
|
||||
echo "No matching serving tests found in $serving_test_file for model='$MODEL_FILTER' dtype='$DTYPE_FILTER'." >&2
|
||||
return 0
|
||||
fi
|
||||
fi
|
||||
|
||||
# Iterate over serving tests (merged + optional filtered stream)
|
||||
merge_serving_tests_stream "$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 [[ ! "$test_name" =~ ^serving_ ]]; then
|
||||
echo "In serving-test.json, test_name must start with \"serving_\"."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# get client and server arguments (after merged the default parameters)
|
||||
server_params=$(echo "$params" | jq -r '.server_parameters')
|
||||
server_envs=$(echo "$params" | jq -r '.server_environment_variables')
|
||||
client_params=$(echo "$params" | jq -r '.client_parameters')
|
||||
|
||||
# vLLM serve CLI: model must be positional (no --model). Convert server_parameters accordingly.
|
||||
server_model=$(echo "$server_params" | jq -r '.model // empty')
|
||||
if [[ -z "$server_model" || "$server_model" == "null" ]]; then
|
||||
echo "Error: serving test '$test_name' is missing server_parameters.model" >&2
|
||||
exit 1
|
||||
fi
|
||||
server_params_no_model=$(echo "$server_params" | jq -c 'del(.model)')
|
||||
server_args=$(json2args "$server_params_no_model")
|
||||
|
||||
server_envs=$(json2envs "$server_envs")
|
||||
client_args=$(json2args "$client_params")
|
||||
|
||||
# ------------------------------------------------------------
|
||||
# Option 1: Dynamic num-prompts scaling based on max_concurrency
|
||||
#
|
||||
# If PROMPTS_PER_CONCURRENCY is set, override JSON num_prompts with:
|
||||
# num_prompts = max_concurrency * PROMPTS_PER_CONCURRENCY
|
||||
#
|
||||
# If PROMPTS_PER_CONCURRENCY is NOT set, keep JSON num_prompts behavior
|
||||
# unchanged (i.e., whatever is in serving-tests-*.json).
|
||||
# ------------------------------------------------------------
|
||||
PROMPTS_PER_CONCURRENCY="${PROMPTS_PER_CONCURRENCY-}" # no default on purpose
|
||||
MIN_NUM_PROMPTS="${MIN_NUM_PROMPTS:-1}"
|
||||
MAX_NUM_PROMPTS="${MAX_NUM_PROMPTS:-1000000}"
|
||||
|
||||
if [[ -n "${PROMPTS_PER_CONCURRENCY}" ]]; then
|
||||
# Remove any fixed --num-prompts from JSON-derived args (avoid duplicates)
|
||||
# Remove any fixed --num-prompts from JSON-derived args (avoid duplicates)
|
||||
# Handles: --num-prompts 123 and --num-prompts=123
|
||||
client_args_no_np="$(
|
||||
printf ' %s ' "$client_args" \
|
||||
| sed -E \
|
||||
-e 's/[[:space:]]--num-prompts=([^[:space:]]+)([[:space:]]|$)/ /g' \
|
||||
-e 's/[[:space:]]--num-prompts[[:space:]]+([^[:space:]]+)([[:space:]]|$)/ /g'
|
||||
)"
|
||||
# normalize whitespace
|
||||
client_args_no_np="$(echo "$client_args_no_np" | tr -s ' ' | sed -E 's/^ //; s/ $//')"
|
||||
client_args_no_np="$(echo "$client_args_no_np" | xargs)"
|
||||
client_args_effective="$client_args_no_np"
|
||||
else
|
||||
client_args_effective="$client_args"
|
||||
fi
|
||||
# qps_list
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# max_concurrency_list (fallback to num_prompts if missing)
|
||||
max_concurrency_list=$(echo "$params" | jq -r '.max_concurrency_list')
|
||||
if [[ -z "$max_concurrency_list" || "$max_concurrency_list" == "null" ]]; then
|
||||
num_prompts=$(echo "$client_params" | jq -r '.num_prompts')
|
||||
max_concurrency_list="[$num_prompts]"
|
||||
fi
|
||||
max_concurrency_list=$(echo "$max_concurrency_list" | jq -r '.[] | @sh')
|
||||
echo "Running over max concurrency list $max_concurrency_list"
|
||||
|
||||
# check if there is enough resources to run the test
|
||||
tp=$(echo "$server_params" | jq -r '.tensor_parallel_size')
|
||||
if [[ "$ON_CPU" == "1" ]]; then
|
||||
pp=$(echo "$server_params" | jq -r '.pipeline_parallel_size // 1')
|
||||
world_size=$(($tp*$pp))
|
||||
if [[ $numa_count -lt $world_size && -z "${REMOTE_HOST}" ]]; then
|
||||
echo "Required world-size $world_size but only $numa_count NUMA nodes found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
else
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
fi
|
||||
|
||||
# check if server model and client model is aligned
|
||||
client_model=$(echo "$client_params" | jq -r '.model')
|
||||
if [[ $server_model != "$client_model" ]]; then
|
||||
echo "Server model and client model must be the same. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
server_command="$server_envs vllm serve $server_model \
|
||||
$server_args"
|
||||
|
||||
# run the server
|
||||
echo "Running test case $test_name"
|
||||
echo "Server command: $server_command"
|
||||
# support remote vllm server
|
||||
client_remote_args=""
|
||||
if [[ -z "${REMOTE_HOST}" && "${DRY_RUN:-0}" != "1" ]]; then
|
||||
bash -c "$server_command" &
|
||||
server_pid=$!
|
||||
# wait until the server is alive
|
||||
if wait_for_server; then
|
||||
echo ""
|
||||
echo "vLLM server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "vLLM failed to start within the timeout period."
|
||||
fi
|
||||
elif [[ "${DRY_RUN:-0}" == "1" ]]; then
|
||||
# dry-run: don't start server
|
||||
echo "Dry Run."
|
||||
else
|
||||
server_command="Using Remote Server $REMOTE_HOST $REMOTE_PORT"
|
||||
if [[ ${REMOTE_PORT} ]]; then
|
||||
client_remote_args=" --host=$REMOTE_HOST --port=$REMOTE_PORT "
|
||||
else
|
||||
client_remote_args=" --host=$REMOTE_HOST "
|
||||
fi
|
||||
fi
|
||||
|
||||
# save the compilation mode and optimization level on the serving results
|
||||
# whenever they are set
|
||||
compilation_config_mode=$(echo "$server_params" | jq -r '."compilation_config.mode" // empty')
|
||||
optimization_level=$(echo "$server_params" | jq -r '.optimization_level // empty')
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
qps="inf"
|
||||
fi
|
||||
|
||||
# iterate over different max_concurrency
|
||||
for max_concurrency in $max_concurrency_list; do
|
||||
new_test_name="${test_name}_qps_${qps}_concurrency_${max_concurrency}"
|
||||
echo " new test name $new_test_name"
|
||||
# If PROMPTS_PER_CONCURRENCY is set, compute per-concurrency --num-prompts.
|
||||
num_prompts_arg=""
|
||||
if [[ -n "${PROMPTS_PER_CONCURRENCY}" ]]; then
|
||||
num_prompts=$(( max_concurrency * PROMPTS_PER_CONCURRENCY ))
|
||||
if (( num_prompts < MIN_NUM_PROMPTS )); then num_prompts=$MIN_NUM_PROMPTS; fi
|
||||
if (( num_prompts > MAX_NUM_PROMPTS )); then num_prompts=$MAX_NUM_PROMPTS; fi
|
||||
num_prompts_arg="--num-prompts $num_prompts"
|
||||
fi
|
||||
# pass the tensor parallel size, the compilation mode, and the optimization
|
||||
# level to the client so that they can be used on the benchmark dashboard
|
||||
client_command="vllm bench serve \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
--max-concurrency $max_concurrency \
|
||||
$num_prompts_arg \
|
||||
--metadata tensor_parallel_size=$tp compilation_config.mode=$compilation_config_mode optimization_level=$optimization_level \
|
||||
$client_args_effective $client_remote_args "
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
if [[ "${DRY_RUN:-0}" != "1" ]]; then
|
||||
bash -c "$client_command"
|
||||
fi
|
||||
|
||||
# record the benchmarking commands
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
done
|
||||
|
||||
adaptive_refine_from_static_results \
|
||||
"$test_name" "$qps" "$max_concurrency_list" "$tp" \
|
||||
"$compilation_config_mode" "$optimization_level" \
|
||||
"$client_args_effective" "$client_remote_args" "$server_command"
|
||||
done
|
||||
|
||||
# clean up
|
||||
if [[ "${DRY_RUN:-0}" != "1" ]]; then
|
||||
kill -9 "$server_pid"
|
||||
kill_gpu_processes
|
||||
fi
|
||||
done
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
local ARCH
|
||||
ARCH=''
|
||||
if [[ "$ON_CPU" == "1" ]]; then
|
||||
check_cpus
|
||||
ARCH="-$gpu_type"
|
||||
else
|
||||
check_gpus
|
||||
ARCH="$arch_suffix"
|
||||
fi
|
||||
|
||||
# DRY_RUN does not execute vLLM; do not require HF_TOKEN.
|
||||
if [[ "${DRY_RUN:-0}" != "1" ]]; then
|
||||
check_hf_token
|
||||
else
|
||||
echo "DRY_RUN=1 -> skip HF_TOKEN validation"
|
||||
fi
|
||||
|
||||
# dependencies
|
||||
(which wget && which curl) || (apt-get update && apt-get install -y wget curl)
|
||||
(which jq) || (apt-get update && apt-get -y install jq)
|
||||
(which lsof) || (apt-get update && apt-get install -y lsof)
|
||||
|
||||
# get the current IP address, required by `vllm bench serve` command
|
||||
export VLLM_HOST_IP=$(hostname -I | awk '{print $1}')
|
||||
# turn of the reporting of the status of each request, to clean up the terminal output
|
||||
export VLLM_LOGGING_LEVEL="WARNING"
|
||||
|
||||
# prepare for benchmarking
|
||||
cd benchmarks || exit 1
|
||||
ensure_sharegpt_downloaded
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
QUICK_BENCHMARK_ROOT=../.buildkite/performance-benchmarks/
|
||||
|
||||
# dump vllm info via vllm collect-env
|
||||
env_output=$(vllm collect-env)
|
||||
echo "$env_output" >"$RESULTS_FOLDER/vllm_env.txt"
|
||||
|
||||
# benchmarking
|
||||
run_serving_tests $QUICK_BENCHMARK_ROOT/tests/"${SERVING_JSON:-serving-tests$ARCH.json}" || exit $?
|
||||
|
||||
if [[ "${DRY_RUN:-0}" == "1" ]]; then
|
||||
echo "DRY_RUN=1 -> skip latency/startup/throughput suites"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
run_latency_tests $QUICK_BENCHMARK_ROOT/tests/"${LATENCY_JSON:-latency-tests$ARCH.json}"
|
||||
run_startup_tests $QUICK_BENCHMARK_ROOT/tests/"${STARTUP_JSON:-startup-tests$ARCH.json}"
|
||||
run_throughput_tests $QUICK_BENCHMARK_ROOT/tests/"${THROUGHPUT_JSON:-throughput-tests$ARCH.json}"
|
||||
|
||||
# postprocess benchmarking results
|
||||
pip install tabulate pandas
|
||||
python3 $QUICK_BENCHMARK_ROOT/scripts/convert-results-json-to-markdown.py
|
||||
python3 $QUICK_BENCHMARK_ROOT/scripts/compare-json-results.py -f $RESULTS_FOLDER/benchmark_results.json
|
||||
|
||||
upload_to_buildkite
|
||||
}
|
||||
|
||||
main "$@"
|
||||
Reference in New Issue
Block a user