biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build][Intel] Add new performance benchmarks for Intel Gaudi 3 (#31025)

Browse Source 
Signed-off-by: Szymon Reginis <sreginis@habana.ai>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
Szymon Reginis
2026-03-03 12:48:24 +01:00
committed by GitHub
parent b8401cde0e
commit 4beebfd146
3 changed files with 192 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
.buildkite/performance-benchmarks/tests/latency-tests-hpu.json
View File

@@ -51,5 +51,56 @@
"max-model-len": 256,
"async-scheduling": ""
}
},
{
"test_name": "latency_deepseek_r1",
"environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"parameters": {
"model": "deepseek-ai/DeepSeek-R1",
"tensor_parallel_size": 8,
"load_format": "dummy",
"max-model-len": 2048,
"dtype": "bfloat16"
}
},
{
"test_name": "latency_llama4_maverick_17b128e_instruct_fp8",
"environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"tensor_parallel_size": 8,
"max-model-len": 512,
"max-num-seqs": 128,
"async-scheduling": "",
"gpu-memory-utilization": 0.95,
"enable_expert_parallel": ""
}
},
{
"test_name": "latency_qwen3_8b",
"environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"parameters": {
"model": "Qwen/Qwen3-8B",
"tensor_parallel_size": 1,
"max-model-len": 2048,
"max-num-seqs": 128,
"dtype": "bfloat16",
"async-scheduling": ""
}
}
]