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
2025-12-19 20:16:18 +08:00
committed by GitHub
parent 455949675d
commit 420ba2dbb6
6 changed files with 213 additions and 18 deletions

View File

@@ -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"
}
}
]