Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
158 lines
5.2 KiB
JSON
158 lines
5.2 KiB
JSON
[
|
|
{
|
|
"test_name": "serving_llama8B_tp1_sharegpt",
|
|
"qps_list": [1, 4, 16, "inf"],
|
|
"server_environment_variables": {
|
|
"PT_HPU_LAZY_MODE": 1,
|
|
"VLLM_CONTIGUOUS_PA": 1,
|
|
"VLLM_DEFRAG": 1
|
|
},
|
|
"server_parameters": {
|
|
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 1,
|
|
"disable_log_stats": "",
|
|
"load_format": "dummy",
|
|
"max-model-len": 2048,
|
|
"max-num-seqs": 256,
|
|
"async-scheduling": ""
|
|
},
|
|
"client_parameters": {
|
|
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
"backend": "vllm",
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"num_prompts": 200
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama70B_tp4_sharegpt",
|
|
"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/Meta-Llama-3.1-70B-Instruct",
|
|
"tensor_parallel_size": 4,
|
|
"disable_log_stats": "",
|
|
"load_format": "dummy",
|
|
"max-model-len": 2048,
|
|
"max-num-seqs": 256,
|
|
"async-scheduling": ""
|
|
},
|
|
"client_parameters": {
|
|
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
|
"backend": "vllm",
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"num_prompts": 200
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_mixtral8x7B_tp2_sharegpt",
|
|
"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": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
|
"tensor_parallel_size": 2,
|
|
"disable_log_stats": "",
|
|
"load_format": "dummy",
|
|
"max-model-len": 2048,
|
|
"max-num-seqs": 256,
|
|
"async-scheduling": ""
|
|
},
|
|
"client_parameters": {
|
|
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
|
"backend": "vllm",
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"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,
|
|
"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
|
|
}
|
|
}
|
|
]
|