mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-24 18:45:02 +08:00
Enable aarch64 CPU performance benchmarks (#26494)
Signed-off-by: Ioana Ghiban <ioana.ghiban@arm.com> Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com> Co-authored-by: Ioana Ghiban <ioana.ghiban@arm.com> Co-authored-by: Fadi Arafeh <fadi.arafeh@arm.com>
This commit is contained in:
Li, Jiang
GitHub
parent
455949675d
commit
420ba2dbb6
@ -7,7 +7,7 @@ vLLM also maintains a continuous performance benchmark under [perf.vllm.ai](http
|
||||
|
||||
## Performance benchmark quick overview
|
||||
|
||||
**Benchmarking Coverage**: latency, throughput and fix-qps serving on B200, A100, H100, Intel® Xeon® Processors and Intel® Gaudi® 3 Accelerators with different models.
|
||||
**Benchmarking Coverage**: latency, throughput and fix-qps serving on B200, A100, H100, Intel® Xeon® Processors, Intel® Gaudi® 3 Accelerators and Arm® Neoverse™ with different models.
|
||||
|
||||
**Benchmarking Duration**: about 1hr.
|
||||
|
||||
@ -23,7 +23,7 @@ bash .buildkite/performance-benchmarks/scripts/run-performance-benchmarks.sh
|
||||
|
||||
Runtime environment variables:
|
||||
|
||||
- `ON_CPU`: set the value to '1' on Intel® Xeon® Processors. Default value is 0.
|
||||
- `ON_CPU`: set the value to '1' on Intel® Xeon® and Arm® Neoverse™ Processors. Default value is 0.
|
||||
- `SERVING_JSON`: JSON file to use for the serving tests. Default value is empty string (use default file).
|
||||
- `LATENCY_JSON`: JSON file to use for the latency tests. Default value is empty string (use default file).
|
||||
- `THROUGHPUT_JSON`: JSON file to use for the throughout tests. Default value is empty string (use default file).
|
||||
@ -34,8 +34,9 @@ Runtime environment variables:
|
||||
|
||||
See [performance-benchmarks-descriptions.md](performance-benchmarks-descriptions.md) for detailed descriptions, and use `tests/latency-tests.json`, `tests/throughput-tests.json`, `tests/serving-tests.json` to configure the test cases.
|
||||
> NOTE: For Intel® Xeon® Processors, use `tests/latency-tests-cpu.json`, `tests/throughput-tests-cpu.json`, `tests/serving-tests-cpu.json` instead.
|
||||
For Intel® Gaudi® 3 Accelerators, use `tests/latency-tests-hpu.json`, `tests/throughput-tests-hpu.json`, `tests/serving-tests-hpu.json` instead.
|
||||
>
|
||||
> For Intel® Gaudi® 3 Accelerators, use `tests/latency-tests-hpu.json`, `tests/throughput-tests-hpu.json`, `tests/serving-tests-hpu.json` instead.
|
||||
> For Arm® Neoverse™, use `tests/latency-tests-arm64-cpu.json`, `tests/throughput-tests-arm64-cpu.json`, `tests/serving-tests-arm64-cpu.json` instead.
|
||||
|
||||
### Latency test
|
||||
|
||||
Here is an example of one test inside `latency-tests.json`:
|
||||
|
||||
24
.buildkite/performance-benchmarks/scripts/run-performance-benchmarks.sh
Normal file → Executable file
24
.buildkite/performance-benchmarks/scripts/run-performance-benchmarks.sh
Normal file → Executable file
@ -49,7 +49,11 @@ check_cpus() {
|
||||
echo "Need at least 1 NUMA to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type="cpu"
|
||||
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 $gpu_type"
|
||||
}
|
||||
|
||||
@ -207,8 +211,8 @@ run_latency_tests() {
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
tp=$(echo "$latency_params" | jq -r '.tensor_parallel_size')
|
||||
if [ "$ON_CPU" == "1" ]; then
|
||||
pp=$(echo "$latency_params" | jq -r '.pipeline_parallel_size')
|
||||
if [[ "$ON_CPU" == "1" ]]; then
|
||||
pp=$(echo "$latency_params" | jq -r '.pipeline_parallel_size // 1')
|
||||
world_size=$(($tp*$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 $test_name."
|
||||
@ -276,8 +280,8 @@ run_throughput_tests() {
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
tp=$(echo "$throughput_params" | jq -r '.tensor_parallel_size')
|
||||
if [ "$ON_CPU" == "1" ]; then
|
||||
pp=$(echo "$throughput_params" | jq -r '.pipeline_parallel_size')
|
||||
if [[ "$ON_CPU" == "1" ]]; then
|
||||
pp=$(echo "$throughput_params" | jq -r '.pipeline_parallel_size // 1')
|
||||
world_size=$(($tp*$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 $test_name."
|
||||
@ -393,8 +397,8 @@ run_serving_tests() {
|
||||
|
||||
# check if there is enough resources to run the test
|
||||
tp=$(echo "$server_params" | jq -r '.tensor_parallel_size')
|
||||
if [ "$ON_CPU" == "1" ]; then
|
||||
pp=$(echo "$server_params" | jq -r '.pipeline_parallel_size')
|
||||
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 $test_name."
|
||||
@ -496,9 +500,9 @@ run_serving_tests() {
|
||||
main() {
|
||||
local ARCH
|
||||
ARCH=''
|
||||
if [ "$ON_CPU" == "1" ];then
|
||||
check_cpus
|
||||
ARCH='-cpu'
|
||||
if [[ "$ON_CPU" == "1" ]]; then
|
||||
check_cpus
|
||||
ARCH="-$gpu_type"
|
||||
else
|
||||
check_gpus
|
||||
ARCH="$arch_suffix"
|
||||
|
||||
@ -0,0 +1,26 @@
|
||||
[
|
||||
{
|
||||
"test_name": "latency_llama8B_tp1",
|
||||
"environment_variables": {
|
||||
"VLLM_RPC_TIMEOUT": 100000,
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"dtype": "bfloat16",
|
||||
"distributed_executor_backend": "mp",
|
||||
"block_size": 128,
|
||||
"trust_remote_code": "",
|
||||
"disable_log_stats": "",
|
||||
"enforce_eager": "",
|
||||
"max_num_batched_tokens": 2048,
|
||||
"max_num_seqs": 256,
|
||||
"num_iters_warmup": 5,
|
||||
"num_iters": 15
|
||||
}
|
||||
}
|
||||
]
|
||||
@ -0,0 +1,130 @@
|
||||
{
|
||||
"defaults": {
|
||||
"qps_list": [
|
||||
"inf"
|
||||
],
|
||||
"max_concurrency_list": [
|
||||
12,
|
||||
16,
|
||||
24,
|
||||
32,
|
||||
64,
|
||||
128,
|
||||
200
|
||||
],
|
||||
"server_environment_variables": {
|
||||
"VLLM_RPC_TIMEOUT": 100000,
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_SGL_KERNEL": 1,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"dtype": "bfloat16",
|
||||
"distributed_executor_backend": "mp",
|
||||
"block_size": 128,
|
||||
"trust_remote_code": "",
|
||||
"disable_log_stats": "",
|
||||
"enforce_eager": "",
|
||||
"max_num_batched_tokens": 2048,
|
||||
"max_num_seqs": 256,
|
||||
"load_format": "dummy"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"backend": "vllm",
|
||||
"ignore-eos": "",
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
"tests": [
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_sharegpt",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_sharegpt",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_128_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_128_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_128_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_2048_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_2048_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 128
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@ -0,0 +1,27 @@
|
||||
[
|
||||
{
|
||||
"test_name": "throughput_llama8B_tp1",
|
||||
"environment_variables": {
|
||||
"VLLM_RPC_TIMEOUT": 100000,
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"dtype": "bfloat16",
|
||||
"distributed_executor_backend": "mp",
|
||||
"block_size": 128,
|
||||
"trust_remote_code": "",
|
||||
"disable_log_stats": "",
|
||||
"enforce_eager": "",
|
||||
"max_num_batched_tokens": 2048,
|
||||
"max_num_seqs": 256,
|
||||
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 200,
|
||||
"backend": "vllm"
|
||||
}
|
||||
}
|
||||
]
|
||||
@ -8,12 +8,19 @@ The results are automatically published to the public [vLLM Performance Dashboar
|
||||
## Manually Trigger the benchmark
|
||||
|
||||
Use [vllm-ci-test-repo images](https://gallery.ecr.aws/q9t5s3a7/vllm-ci-test-repo) with vLLM benchmark suite.
|
||||
For CPU environment, please use the image with "-cpu" postfix.
|
||||
For x86 CPU environment, please use the image with "-cpu" postfix. For AArch64 CPU environment, please use the image with "-arm64-cpu" postfix.
|
||||
|
||||
Here is an example for docker run command for CPU.
|
||||
Here is an example for docker run command for CPU. For GPUs skip setting the `ON_CPU` env var.
|
||||
|
||||
```bash
|
||||
docker run -it --entrypoint /bin/bash -v /data/huggingface:/root/.cache/huggingface -e HF_TOKEN='' --shm-size=16g --name vllm-cpu-ci public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:1da94e673c257373280026f75ceb4effac80e892-cpu
|
||||
export VLLM_COMMIT=1da94e673c257373280026f75ceb4effac80e892 # use full commit hash from the main branch
|
||||
export HF_TOKEN=<valid Hugging Face token>
|
||||
if [[ "$(uname -m)" == aarch64 || "$(uname -m)" == arm64 ]]; then
|
||||
IMG_SUFFIX="arm64-cpu"
|
||||
else
|
||||
IMG_SUFFIX="cpu"
|
||||
fi
|
||||
docker run -it --entrypoint /bin/bash -v /data/huggingface:/root/.cache/huggingface -e HF_TOKEN=$HF_TOKEN -e ON_ARM64_CPU=1 --shm-size=16g --name vllm-cpu-ci public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:${VLLM_COMMIT}-${IMG_SUFFIX}
|
||||
```
|
||||
|
||||
Then, run below command inside the docker instance.
|
||||
@ -26,7 +33,7 @@ When run, benchmark script generates results under **benchmark/results** folder,
|
||||
|
||||
### Runtime environment variables
|
||||
|
||||
- `ON_CPU`: set the value to '1' on Intel® Xeon® Processors. Default value is 0.
|
||||
- `ON_CPU`: set the value to '1' on Intel® Xeon® and Arm® Neoverse™ Processors. Default value is 0.
|
||||
- `SERVING_JSON`: JSON file to use for the serving tests. Default value is empty string (use default file).
|
||||
- `LATENCY_JSON`: JSON file to use for the latency tests. Default value is empty string (use default file).
|
||||
- `THROUGHPUT_JSON`: JSON file to use for the throughout tests. Default value is empty string (use default file).
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user