Skip to content

GitLab

Unverified Commit 4beebfd1 authored by Szymon Reginis's avatar Szymon Reginis Committed by GitHub
Browse files

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


Signed-off-by: default avatarSzymon Reginis <sreginis@habana.ai>
Co-authored-by: default avatarKunshang Ji <kunshang.ji@intel.com>
parent b8401cde
Hide whitespace changes
Inline Side-by-side
Showing with 192 additions and 0 deletions
.buildkite/performance-benchmarks/tests/latency-tests-hpu.json
View file @ 4beebfd1
...@@ -51,5 +51,56 @@ ...@@ -51,5 +51,56 @@
"max-model-len": 256, "max-model-len": 256,
"async-scheduling": "" "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": ""
}
} }
] ]
.buildkite/performance-benchmarks/tests/serving-tests-hpu.json
View file @ 4beebfd1
...@@ -78,5 +78,84 @@ ...@@ -78,5 +78,84 @@
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json", "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200 "num_prompts": 200
} }
},
{
"test_name": "serving_deepseek_r1",
"qps_list": [1, 4, 16, "inf"],
"server_environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"server_parameters": {
"model": "deepseek-ai/DeepSeek-R1",
"tensor_parallel_size": 8,
"swap_space": 16,
"disable_log_stats": "",
"load_format": "dummy",
"max-model-len": 2048,
"max-num-seqs": 200,
"async-scheduling": "",
"dtype": "bfloat16"
},
"client_parameters": {
"model": "deepseek-ai/DeepSeek-R1",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_llama4_maverick_17b128e_instruct_fp8",
"qps_list": [1, 4, 16, "inf"],
"server_environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"server_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"tensor_parallel_size": 8,
"disable_log_stats": "",
"max-model-len": 2048,
"max-num-seqs": 128,
"async-scheduling": "",
"enable_expert_parallel": "",
"max-num-batched-tokens": 4096
},
"client_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_qwen3_8b",
"qps_list": [1, 4, 10, "inf"],
"server_environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"server_parameters": {
"model": "Qwen/Qwen-3-8B",
"tensor_parallel_size": 1,
"dtype": "bfloat16",
"disable_log_stats": "",
"async-scheduling": ""
},
"client_parameters": {
"model": "Qwen/Qwen-3-8B",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
} }
] ]
.buildkite/performance-benchmarks/tests/throughput-tests-hpu.json
View file @ 4beebfd1
...@@ -57,5 +57,67 @@ ...@@ -57,5 +57,67 @@
"max-num-seqs": 512, "max-num-seqs": 512,
"async-scheduling": "" "async-scheduling": ""
} }
},
{
"test_name": "throughput_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",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"dataset_name": "sharegpt",
"num_prompts": 1000,
"backend": "vllm",
"max-model-len": 2048,
"max-num-seqs": 384,
"async-scheduling": ""
}
},
{
"test_name": "throughput_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,
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"dataset_name": "sharegpt",
"num_prompts": 1000,
"backend": "vllm",
"max-model-len": 2048,
"max-num-seqs": 512,
"async-scheduling": "",
"enable_expert_parallel": ""
}
},
{
"test_name": "throughput_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/Qwen-3-8B",
"tensor_parallel_size": 1,
"load_format": "dummy",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"dataset_name": "sharegpt",
"num_prompts": 1000,
"max-num-seqs": 512,
"backend": "vllm",
"async-scheduling": ""
}
} }
] ]
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment