[Benchmark] Cleanup deprecated nightly benchmark and adjust the docstring for performance benchmark (#25786)
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
This commit is contained in:
Kuntai Du
@@ -0,0 +1,456 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
from importlib import util
|
||||
|
||||
import pandas as pd
|
||||
|
||||
pd.options.display.float_format = "{:.2f}".format
|
||||
plotly_found = util.find_spec("plotly.express") is not None
|
||||
|
||||
|
||||
def compare_data_columns(
|
||||
files, name_column, data_column, info_cols, drop_column, debug=False
|
||||
):
|
||||
"""
|
||||
Align concatenation by keys derived from info_cols instead of row order.
|
||||
- Pick one canonical key list: subset of info_cols present in ALL files.
|
||||
- For each file: set index to those keys, aggregate duplicates
|
||||
- (mean for metric, first for names).
|
||||
- Concat along axis=1 (indexes align), then reset_index so callers can
|
||||
- group by columns.
|
||||
- If --debug, add a <file_label>_name column per file.
|
||||
"""
|
||||
print("\ncompare_data_column:", data_column)
|
||||
|
||||
frames = []
|
||||
raw_data_cols = []
|
||||
compare_frames = []
|
||||
|
||||
# 1) choose a canonical key list from info_cols that exists in ALL files
|
||||
cols_per_file = []
|
||||
for f in files:
|
||||
try:
|
||||
df_tmp = pd.read_json(f, orient="records")
|
||||
except Exception as err:
|
||||
raise ValueError(f"Failed to read {f}") from err
|
||||
cols_per_file.append(set(df_tmp.columns))
|
||||
|
||||
key_cols = [c for c in info_cols if all(c in cset for cset in cols_per_file)]
|
||||
if not key_cols:
|
||||
# soft fallback: use any info_cols present in the first file
|
||||
key_cols = [c for c in info_cols if c in list(cols_per_file[0])]
|
||||
if not key_cols:
|
||||
raise ValueError(
|
||||
"No common key columns found from info_cols across the input files."
|
||||
)
|
||||
|
||||
# 2) build a single "meta" block (keys as columns) once, aligned by the key index
|
||||
meta_added = False
|
||||
|
||||
for file in files:
|
||||
df = pd.read_json(file, orient="records")
|
||||
|
||||
# Keep rows that actually have the compared metric (same as original behavior)
|
||||
if drop_column in df.columns:
|
||||
df = df.dropna(subset=[drop_column], ignore_index=True)
|
||||
|
||||
# Stabilize numeric key columns (harmless if missing)
|
||||
for c in (
|
||||
"Input Len",
|
||||
"Output Len",
|
||||
"TP Size",
|
||||
"PP Size",
|
||||
"# of max concurrency.",
|
||||
"qps",
|
||||
):
|
||||
if c in df.columns:
|
||||
df[c] = pd.to_numeric(df[c], errors="coerce")
|
||||
|
||||
# Ensure all key columns exist
|
||||
for c in key_cols:
|
||||
if c not in df.columns:
|
||||
df[c] = pd.NA
|
||||
|
||||
# Set index = key_cols and aggregate duplicates → unique MultiIndex
|
||||
df_idx = df.set_index(key_cols, drop=False)
|
||||
|
||||
# meta (key columns), unique per key
|
||||
meta = df_idx[key_cols]
|
||||
if not meta.index.is_unique:
|
||||
meta = meta.groupby(level=key_cols, dropna=False).first()
|
||||
|
||||
# metric series for this file, aggregated to one row per key
|
||||
file_label = "/".join(file.split("/")[:-1]) or os.path.basename(file)
|
||||
s = df_idx[data_column]
|
||||
if not s.index.is_unique:
|
||||
s = s.groupby(level=key_cols, dropna=False).mean()
|
||||
s.name = file_label # column label like original
|
||||
|
||||
# add meta once (from first file) so keys are the leftmost columns
|
||||
if not meta_added:
|
||||
frames.append(meta)
|
||||
meta_added = True
|
||||
|
||||
# (NEW) debug: aligned test-name column per file
|
||||
if debug and name_column in df_idx.columns:
|
||||
name_s = df_idx[name_column]
|
||||
if not name_s.index.is_unique:
|
||||
name_s = name_s.groupby(level=key_cols, dropna=False).first()
|
||||
name_s.name = f"{file_label}_name"
|
||||
frames.append(name_s)
|
||||
|
||||
frames.append(s)
|
||||
raw_data_cols.append(file_label)
|
||||
compare_frames.append(s)
|
||||
|
||||
# Generalize ratio: for any file N>=2, add ratio (fileN / file1)
|
||||
if len(compare_frames) >= 2:
|
||||
base = compare_frames[0]
|
||||
current = compare_frames[-1]
|
||||
if "P99" in data_column or "Median" in data_column:
|
||||
ratio = base / current # for latency
|
||||
else:
|
||||
ratio = current / base
|
||||
ratio = ratio.mask(base == 0) # avoid inf when baseline is 0
|
||||
ratio.name = f"Ratio 1 vs {len(compare_frames)}"
|
||||
frames.append(ratio)
|
||||
|
||||
# 4) concat on columns with aligned MultiIndex;
|
||||
# then reset_index to return keys as columns
|
||||
concat_df = pd.concat(frames, axis=1)
|
||||
concat_df = concat_df.reset_index(drop=True).reset_index()
|
||||
if "index" in concat_df.columns:
|
||||
concat_df = concat_df.drop(columns=["index"])
|
||||
|
||||
# Ensure key/info columns appear first (in your info_cols order)
|
||||
front = [c for c in info_cols if c in concat_df.columns]
|
||||
rest = [c for c in concat_df.columns if c not in front]
|
||||
concat_df = concat_df[front + rest]
|
||||
|
||||
print(raw_data_cols)
|
||||
return concat_df, raw_data_cols
|
||||
|
||||
|
||||
def split_json_by_tp_pp(
|
||||
input_file: str = "benchmark_results.json", output_root: str = "."
|
||||
) -> list[str]:
|
||||
"""
|
||||
Split a benchmark JSON into separate folders by (TP Size, PP Size).
|
||||
|
||||
Creates: <output_root>/tp{TP}_pp{PP}/benchmark_results.json
|
||||
Returns: list of file paths written.
|
||||
"""
|
||||
# Load JSON data into DataFrame
|
||||
with open(input_file, encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
|
||||
# If the JSON is a dict with a list under common keys, use that list
|
||||
if isinstance(data, dict):
|
||||
for key in ("results", "serving_results", "benchmarks", "data"):
|
||||
if isinstance(data.get(key), list):
|
||||
data = data[key]
|
||||
break
|
||||
|
||||
df = pd.DataFrame(data)
|
||||
|
||||
# Keep only "serving" tests
|
||||
name_col = next(
|
||||
(c for c in ["Test name", "test_name", "Test Name"] if c in df.columns), None
|
||||
)
|
||||
if name_col:
|
||||
df = df[
|
||||
df[name_col].astype(str).str.contains(r"serving", case=False, na=False)
|
||||
].copy()
|
||||
|
||||
# Handle alias column names
|
||||
rename_map = {
|
||||
"tp_size": "TP Size",
|
||||
"tensor_parallel_size": "TP Size",
|
||||
"pp_size": "PP Size",
|
||||
"pipeline_parallel_size": "PP Size",
|
||||
}
|
||||
df.rename(
|
||||
columns={k: v for k, v in rename_map.items() if k in df.columns}, inplace=True
|
||||
)
|
||||
|
||||
# Ensure TP/PP columns exist (default to 1 if missing)
|
||||
if "TP Size" not in df.columns:
|
||||
df["TP Size"] = 1
|
||||
if "PP Size" not in df.columns:
|
||||
df["PP Size"] = 1
|
||||
|
||||
# make sure TP/PP are numeric ints with no NaN
|
||||
df["TP Size"] = (
|
||||
pd.to_numeric(df.get("TP Size", 1), errors="coerce").fillna(1).astype(int)
|
||||
)
|
||||
df["PP Size"] = (
|
||||
pd.to_numeric(df.get("PP Size", 1), errors="coerce").fillna(1).astype(int)
|
||||
)
|
||||
|
||||
# Split into separate folders
|
||||
saved_paths: list[str] = []
|
||||
for (tp, pp), group_df in df.groupby(["TP Size", "PP Size"], dropna=False):
|
||||
folder_name = os.path.join(output_root, f"tp{int(tp)}_pp{int(pp)}")
|
||||
os.makedirs(folder_name, exist_ok=True)
|
||||
filepath = os.path.join(folder_name, "benchmark_results.json")
|
||||
group_df.to_json(filepath, orient="records", indent=2, force_ascii=False)
|
||||
print(f"Saved: {filepath}")
|
||||
saved_paths.append(filepath)
|
||||
|
||||
return saved_paths
|
||||
|
||||
|
||||
def _add_limit_line(fig, y_value, label):
|
||||
# Visible dashed line + annotation
|
||||
fig.add_hline(
|
||||
y=y_value,
|
||||
line_dash="dash",
|
||||
line_color="red" if "ttft" in label.lower() else "blue",
|
||||
annotation_text=f"{label}: {y_value} ms",
|
||||
annotation_position="top left",
|
||||
)
|
||||
# Optional: add a legend item (as a transparent helper trace)
|
||||
if plot and plotly_found:
|
||||
import plotly.graph_objects as go
|
||||
|
||||
fig.add_trace(
|
||||
go.Scatter(
|
||||
x=[None],
|
||||
y=[None],
|
||||
mode="lines",
|
||||
line=dict(
|
||||
dash="dash", color="red" if "ttft" in label.lower() else "blue"
|
||||
),
|
||||
name=f"{label}",
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def _find_concurrency_col(df: pd.DataFrame) -> str:
|
||||
for c in [
|
||||
"# of max concurrency.",
|
||||
"# of max concurrency",
|
||||
"Max Concurrency",
|
||||
"max_concurrency",
|
||||
"Concurrency",
|
||||
]:
|
||||
if c in df.columns:
|
||||
return c
|
||||
# Fallback: guess an integer-like column (harmless if unused)
|
||||
for c in df.columns:
|
||||
if df[c].dtype.kind in "iu" and df[c].nunique() > 1 and df[c].min() >= 1:
|
||||
return c
|
||||
return "# of max concurrency."
|
||||
|
||||
|
||||
def _highlight_threshold(
|
||||
df: pd.DataFrame, threshold: float
|
||||
) -> "pd.io.formats.style.Styler":
|
||||
"""Highlight numeric per-configuration columns with value <= threshold."""
|
||||
conc_col = _find_concurrency_col(df)
|
||||
key_cols = [
|
||||
c
|
||||
for c in ["Model", "Dataset Name", "Input Len", "Output Len", conc_col]
|
||||
if c in df.columns
|
||||
]
|
||||
conf_cols = [
|
||||
c for c in df.columns if c not in key_cols and not str(c).startswith("Ratio")
|
||||
]
|
||||
conf_cols = [c for c in conf_cols if pd.api.types.is_numeric_dtype(df[c])]
|
||||
return df.style.map(
|
||||
lambda v: "background-color:#e6ffe6;font-weight:bold;"
|
||||
if pd.notna(v) and v <= threshold
|
||||
else "",
|
||||
subset=conf_cols,
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument(
|
||||
"-f", "--file", action="append", type=str, help="input file name"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--debug", action="store_true", help="show all information for debugging"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--plot",
|
||||
action=argparse.BooleanOptionalAction,
|
||||
default=True,
|
||||
help="plot perf diagrams or not --no-plot --plot",
|
||||
)
|
||||
parser.add_argument(
|
||||
"-x",
|
||||
"--xaxis",
|
||||
type=str,
|
||||
default="# of max concurrency.",
|
||||
help="column name to use as X Axis in comparison graph",
|
||||
)
|
||||
parser.add_argument(
|
||||
"-l",
|
||||
"--latency",
|
||||
type=str,
|
||||
default="p99",
|
||||
help="take median|p99 for latency like TTFT/TPOT",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--ttft-max-ms",
|
||||
type=float,
|
||||
default=3000.0,
|
||||
help="Reference limit for TTFT plots (ms)",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--tpot-max-ms",
|
||||
type=float,
|
||||
default=100.0,
|
||||
help="Reference limit for TPOT plots (ms)",
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
drop_column = "P99"
|
||||
name_column = "Test name"
|
||||
info_cols = [
|
||||
"Model",
|
||||
"Dataset Name",
|
||||
"Input Len",
|
||||
"Output Len",
|
||||
"TP Size",
|
||||
"PP Size",
|
||||
"# of max concurrency.",
|
||||
"qps",
|
||||
]
|
||||
|
||||
if "median" in args.latency:
|
||||
data_cols_to_compare = ["Output Tput (tok/s)", "Median TTFT (ms)", "Median"]
|
||||
html_msgs_for_data_cols = [
|
||||
"Compare Output Tokens /n",
|
||||
"Median TTFT /n",
|
||||
"Median TPOT /n",
|
||||
]
|
||||
drop_column = "P99"
|
||||
elif "p99" in args.latency:
|
||||
data_cols_to_compare = ["Output Tput (tok/s)", "P99 TTFT (ms)", "P99"]
|
||||
html_msgs_for_data_cols = [
|
||||
"Compare Output Tokens /n",
|
||||
"P99 TTFT /n",
|
||||
"P99 TPOT /n",
|
||||
]
|
||||
|
||||
if len(args.file) == 1:
|
||||
files = split_json_by_tp_pp(args.file[0], output_root="splits")
|
||||
info_cols = [c for c in info_cols if c not in ("TP Size", "PP Size")]
|
||||
else:
|
||||
files = args.file
|
||||
print("comparing : " + ", ".join(files))
|
||||
debug = args.debug
|
||||
plot = args.plot
|
||||
# For Plot feature, assign y axis from one of info_cols
|
||||
y_axis_index = info_cols.index(args.xaxis) if args.xaxis in info_cols else 6
|
||||
with open("perf_comparison.html", "w") as text_file:
|
||||
for i in range(len(data_cols_to_compare)):
|
||||
output_df, raw_data_cols = compare_data_columns(
|
||||
files,
|
||||
name_column,
|
||||
data_cols_to_compare[i],
|
||||
info_cols,
|
||||
drop_column,
|
||||
debug=debug,
|
||||
)
|
||||
|
||||
# For Plot feature, insert y axis from one of info_cols
|
||||
raw_data_cols.insert(0, info_cols[y_axis_index])
|
||||
|
||||
filtered_info_cols = info_cols[:-2]
|
||||
existing_group_cols = [
|
||||
c for c in filtered_info_cols if c in output_df.columns
|
||||
]
|
||||
if not existing_group_cols:
|
||||
raise ValueError(
|
||||
f"No valid group-by columns "
|
||||
f"Expected subset: {filtered_info_cols}, "
|
||||
f"but DataFrame has: {list(output_df.columns)}"
|
||||
)
|
||||
# output_df_sorted = output_df.sort_values(by=existing_group_cols)
|
||||
output_df_sorted = output_df.sort_values(by=args.xaxis)
|
||||
output_groups = output_df_sorted.groupby(existing_group_cols, dropna=False)
|
||||
for name, group in output_groups:
|
||||
group_name = (
|
||||
",".join(map(str, name)).replace(",", "_").replace("/", "-")
|
||||
)
|
||||
group_html_name = "perf_comparison_" + group_name + ".html"
|
||||
|
||||
metric_name = str(data_cols_to_compare[i]).lower()
|
||||
if "tok/s" in metric_name:
|
||||
html = group.to_html()
|
||||
elif "ttft" in metric_name:
|
||||
styler = _highlight_threshold(group, args.ttft_max_ms).format(
|
||||
{c: "{:.2f}" for c in group.select_dtypes("number").columns},
|
||||
na_rep="—",
|
||||
)
|
||||
html = styler.to_html(
|
||||
table_attributes='border="1" class="dataframe"'
|
||||
)
|
||||
elif (
|
||||
"tpot" in metric_name
|
||||
or "median" in metric_name
|
||||
or "p99" in metric_name
|
||||
):
|
||||
styler = _highlight_threshold(group, args.tpot_max_ms).format(
|
||||
{c: "{:.2f}" for c in group.select_dtypes("number").columns},
|
||||
na_rep="—",
|
||||
)
|
||||
html = styler.to_html(
|
||||
table_attributes='border="1" class="dataframe"'
|
||||
)
|
||||
|
||||
text_file.write(html_msgs_for_data_cols[i])
|
||||
text_file.write(html)
|
||||
with open(group_html_name, "a+") as sub_text_file:
|
||||
sub_text_file.write(html_msgs_for_data_cols[i])
|
||||
sub_text_file.write(html)
|
||||
|
||||
if plot and plotly_found:
|
||||
import plotly.express as px
|
||||
|
||||
df = group[raw_data_cols]
|
||||
df_sorted = df.sort_values(by=info_cols[y_axis_index])
|
||||
# Melt DataFrame for plotting
|
||||
df_melted = df_sorted.melt(
|
||||
id_vars=info_cols[y_axis_index],
|
||||
var_name="Configuration",
|
||||
value_name=data_cols_to_compare[i],
|
||||
)
|
||||
title = (
|
||||
data_cols_to_compare[i] + " vs " + info_cols[y_axis_index]
|
||||
)
|
||||
# Create Plotly line chart
|
||||
fig = px.line(
|
||||
df_melted,
|
||||
x=info_cols[y_axis_index],
|
||||
y=data_cols_to_compare[i],
|
||||
color="Configuration",
|
||||
title=title,
|
||||
markers=True,
|
||||
)
|
||||
|
||||
# ---- Add threshold lines based on metric name ----
|
||||
if "ttft" in metric_name:
|
||||
_add_limit_line(fig, args.ttft_max_ms, "TTFT limit")
|
||||
elif (
|
||||
"tpot" in metric_name
|
||||
or "median" in metric_name
|
||||
or "p99" in metric_name
|
||||
):
|
||||
_add_limit_line(fig, args.tpot_max_ms, "TPOT limit")
|
||||
|
||||
# Export to HTML
|
||||
text_file.write(
|
||||
fig.to_html(full_html=True, include_plotlyjs="cdn")
|
||||
)
|
||||
sub_text_file.write(
|
||||
fig.to_html(full_html=True, include_plotlyjs="cdn")
|
||||
)
|
||||
@@ -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
.buildkite/performance-benchmarks/scripts/launch-server.sh
Normal file
224
.buildkite/performance-benchmarks/scripts/launch-server.sh
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 [[ "$CURRENT_LLM_SERVING_ENGINE" == *"vllm"* ]]; then
|
||||
launch_vllm_server
|
||||
fi
|
||||
}
|
||||
|
||||
main
|
||||
@@ -0,0 +1,491 @@
|
||||
#!/bin/bash
|
||||
|
||||
# This script should be run inside the CI process
|
||||
# This script assumes that we are already inside the vllm/ directory
|
||||
# Benchmarking results will be available inside vllm/benchmarks/results/
|
||||
|
||||
# Do not set -e, as the mixtral 8x22B model tends to crash occasionally
|
||||
# and we still want to see other benchmarking results even when mixtral crashes.
|
||||
set -x
|
||||
set -o pipefail
|
||||
|
||||
check_gpus() {
|
||||
if command -v nvidia-smi; then
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
elif command -v amd-smi; then
|
||||
declare -g gpu_count=$(amd-smi list | grep 'GPU' | wc -l)
|
||||
fi
|
||||
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
if command -v nvidia-smi; then
|
||||
declare -g gpu_type=$(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}')
|
||||
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
|
||||
declare -g gpu_type="cpu"
|
||||
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() {
|
||||
# wait for vllm server to start
|
||||
# return 1 if vllm server crashes
|
||||
timeout 1200 bash -c '
|
||||
until curl -X POST localhost:8000/v1/completions; do
|
||||
sleep 1
|
||||
done' && return 0 || return 1
|
||||
}
|
||||
|
||||
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
|
||||
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/*"
|
||||
}
|
||||
|
||||
run_latency_tests() {
|
||||
# run latency tests using `vllm bench latency` command
|
||||
# $1: a json file specifying latency test cases
|
||||
|
||||
local latency_test_file
|
||||
latency_test_file=$1
|
||||
|
||||
# Iterate over latency tests
|
||||
jq -c '.[]' "$latency_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 [[ ! "$test_name" =~ ^latency_ ]]; then
|
||||
echo "In latency-test.json, test_name must start with \"latency_\"."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# get arguments
|
||||
latency_params=$(echo "$params" | jq -r '.parameters')
|
||||
latency_args=$(json2args "$latency_params")
|
||||
latency_environment_variables=$(echo "$params" | jq -r '.environment_variables')
|
||||
latency_envs=$(json2envs "$latency_environment_variables")
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
tp=$(echo "$latency_params" | jq -r '.tensor_parallel_size')
|
||||
if [ "$ON_CPU" == "1" ]; then
|
||||
pp=$(echo "$latency_params" | jq -r '.pipeline_parallel_size')
|
||||
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
|
||||
|
||||
latency_command=" $latency_envs vllm bench latency \
|
||||
--output-json $RESULTS_FOLDER/${test_name}.json \
|
||||
$latency_args"
|
||||
|
||||
echo "Running test case $test_name"
|
||||
echo "Latency command: $latency_command"
|
||||
|
||||
# recoding benchmarking command ang GPU command
|
||||
jq_output=$(jq -n \
|
||||
--arg latency "$latency_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
'{
|
||||
latency_command: $latency,
|
||||
gpu_type: $gpu
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/$test_name.commands"
|
||||
|
||||
# run the benchmark
|
||||
eval "$latency_command"
|
||||
|
||||
kill_gpu_processes
|
||||
|
||||
done
|
||||
}
|
||||
|
||||
run_throughput_tests() {
|
||||
# run throughput tests using `vllm bench throughput`
|
||||
# $1: a json file specifying throughput test cases
|
||||
|
||||
local throughput_test_file
|
||||
throughput_test_file=$1
|
||||
|
||||
# Iterate over throughput tests
|
||||
jq -c '.[]' "$throughput_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 [[ ! "$test_name" =~ ^throughput_ ]]; then
|
||||
echo "In throughput-test.json, test_name must start with \"throughput_\"."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# get arguments
|
||||
throughput_params=$(echo "$params" | jq -r '.parameters')
|
||||
throughput_args=$(json2args "$throughput_params")
|
||||
throughput_environment_variables=$(echo "$params" | jq -r '.environment_variables')
|
||||
throughput_envs=$(json2envs "$throughput_environment_variables")
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
tp=$(echo "$throughput_params" | jq -r '.tensor_parallel_size')
|
||||
if [ "$ON_CPU" == "1" ]; then
|
||||
pp=$(echo "$throughput_params" | jq -r '.pipeline_parallel_size')
|
||||
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
|
||||
|
||||
throughput_command=" $throughput_envs vllm bench throughput \
|
||||
--output-json $RESULTS_FOLDER/${test_name}.json \
|
||||
$throughput_args"
|
||||
|
||||
echo "Running test case $test_name"
|
||||
echo "Throughput command: $throughput_command"
|
||||
# recoding benchmarking command ang GPU command
|
||||
jq_output=$(jq -n \
|
||||
--arg command "$throughput_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
'{
|
||||
throughput_command: $command,
|
||||
gpu_type: $gpu
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/$test_name.commands"
|
||||
|
||||
# run the benchmark
|
||||
eval "$throughput_command"
|
||||
|
||||
kill_gpu_processes
|
||||
|
||||
done
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `vllm bench serve` command
|
||||
# $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 [[ ! "$test_name" =~ ^serving_ ]]; then
|
||||
echo "In serving-test.json, test_name must start with \"serving_\"."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# get client and server arguments
|
||||
server_params=$(echo "$params" | jq -r '.server_parameters')
|
||||
server_envs=$(echo "$params" | jq -r '.server_environment_variables')
|
||||
client_params=$(echo "$params" | jq -r '.client_parameters')
|
||||
server_args=$(json2args "$server_params")
|
||||
server_envs=$(json2envs "$server_envs")
|
||||
client_args=$(json2args "$client_params")
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
max_concurrency_list=$(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')
|
||||
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 $test_name."
|
||||
continue
|
||||
fi
|
||||
fi
|
||||
|
||||
# check if server model and client model is aligned
|
||||
server_model=$(echo "$server_params" | jq -r '.model')
|
||||
client_model=$(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_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}" ]]; 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
|
||||
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
|
||||
|
||||
# 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
|
||||
|
||||
# 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"
|
||||
# pass the tensor parallel size to the client so that it can be displayed
|
||||
# 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 $max_concurrency \
|
||||
--metadata "tensor_parallel_size=$tp" \
|
||||
$client_args $client_remote_args "
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
bash -c "$client_command"
|
||||
|
||||
# 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
|
||||
done
|
||||
|
||||
# clean up
|
||||
kill -9 $server_pid
|
||||
kill_gpu_processes
|
||||
done
|
||||
}
|
||||
|
||||
main() {
|
||||
local ARCH
|
||||
ARCH=''
|
||||
if [ "$ON_CPU" == "1" ];then
|
||||
check_cpus
|
||||
ARCH='-cpu'
|
||||
else
|
||||
check_gpus
|
||||
fi
|
||||
check_hf_token
|
||||
|
||||
# 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}"
|
||||
run_latency_tests $QUICK_BENCHMARK_ROOT/tests/"${LATENCY_JSON:-latency-tests$ARCH.json}"
|
||||
run_throughput_tests $QUICK_BENCHMARK_ROOT/tests/"${THROUGHPUT_JSON:-throughput-tests$ARCH.json}"
|
||||
|
||||
# postprocess benchmarking results
|
||||
pip install tabulate pandas
|
||||
python3 $QUICK_BENCHMARK_ROOT/scripts/convert-results-json-to-markdown.py
|
||||
|
||||
upload_to_buildkite
|
||||
}
|
||||
|
||||
main "$@"
|
||||
Reference in New Issue
Block a user