Files
vllm/.buildkite/nightly-benchmarks/tests/latency-tests-cpu.json
Louie Tsai 00e3f9da46 vLLM Benchmark suite improvement (#22119)
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
Signed-off-by: Louie Tsai <louie.tsai@intel.com>
Co-authored-by: Li, Jiang <bigpyj64@gmail.com>
2025-08-14 07:12:17 +00:00

31 lines
817 B
JSON

[
{
"test_name": "latency_llama8B_tp1",
"environment_variables": {
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"load_format": "dummy",
"num_iters_warmup": 5,
"num_iters": 15
}
},
{
"test_name": "latency_llama8B_tp4",
"environment_variables": {
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 4,
"load_format": "dummy",
"num_iters_warmup": 5,
"num_iters": 15
}
}
]