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>
130 lines
3.1 KiB
JSON
130 lines
3.1 KiB
JSON
{
|
|
"defaults": {
|
|
"qps_list": [
|
|
"inf"
|
|
],
|
|
"max_concurrency_list": [
|
|
12,
|
|
16,
|
|
24,
|
|
32,
|
|
64,
|
|
128,
|
|
200
|
|
],
|
|
"server_environment_variables": {
|
|
"VLLM_RPC_TIMEOUT": 100000,
|
|
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
|
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
|
"VLLM_CPU_SGL_KERNEL": 1,
|
|
"VLLM_CPU_KVCACHE_SPACE": 40
|
|
},
|
|
"server_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 1,
|
|
"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,
|
|
"load_format": "dummy"
|
|
},
|
|
"client_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"backend": "vllm",
|
|
"ignore-eos": "",
|
|
"num_prompts": 200
|
|
}
|
|
},
|
|
"tests": [
|
|
{
|
|
"test_name": "serving_llama8B_tp1_sharegpt",
|
|
"server_parameters": {
|
|
"tensor_parallel_size": 1
|
|
},
|
|
"client_parameters": {
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_tp2_sharegpt",
|
|
"server_parameters": {
|
|
"tensor_parallel_size": 2
|
|
},
|
|
"client_parameters": {
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_tp1_random_128_128",
|
|
"server_parameters": {
|
|
"tensor_parallel_size": 1
|
|
},
|
|
"client_parameters": {
|
|
"dataset_name": "random",
|
|
"random-input-len": 128,
|
|
"random-output-len": 128
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_tp2_random_128_128",
|
|
"server_parameters": {
|
|
"tensor_parallel_size": 2
|
|
},
|
|
"client_parameters": {
|
|
"dataset_name": "random",
|
|
"random-input-len": 128,
|
|
"random-output-len": 128
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_tp1_random_128_2048",
|
|
"server_parameters": {
|
|
"tensor_parallel_size": 1
|
|
},
|
|
"client_parameters": {
|
|
"dataset_name": "random",
|
|
"random-input-len": 128,
|
|
"random-output-len": 2048
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_tp2_random_128_2048",
|
|
"server_parameters": {
|
|
"tensor_parallel_size": 2
|
|
},
|
|
"client_parameters": {
|
|
"dataset_name": "random",
|
|
"random-input-len": 128,
|
|
"random-output-len": 2048
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_tp1_random_2048_128",
|
|
"server_parameters": {
|
|
"tensor_parallel_size": 1
|
|
},
|
|
"client_parameters": {
|
|
"dataset_name": "random",
|
|
"random-input-len": 2048,
|
|
"random-output-len": 128
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_tp2_random_2048_128",
|
|
"server_parameters": {
|
|
"tensor_parallel_size": 2
|
|
},
|
|
"client_parameters": {
|
|
"dataset_name": "random",
|
|
"random-input-len": 2048,
|
|
"random-output-len": 128
|
|
}
|
|
}
|
|
]
|
|
} |