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>
74 lines
2.5 KiB
JSON
74 lines
2.5 KiB
JSON
[
|
|
{
|
|
"test_name": "serving_llama8B_tp1_sharegpt",
|
|
"qps_list": [1, 4, 16, "inf"],
|
|
"server_parameters": {
|
|
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 1,
|
|
"disable_log_stats": "",
|
|
"load_format": "dummy"
|
|
},
|
|
"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_parameters": {
|
|
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
|
"tensor_parallel_size": 4,
|
|
"disable_log_stats": "",
|
|
"load_format": "dummy"
|
|
},
|
|
"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_parameters": {
|
|
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
|
"tensor_parallel_size": 2,
|
|
"disable_log_stats": "",
|
|
"load_format": "dummy"
|
|
},
|
|
"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_llama70B_tp4_sharegpt_specdecode",
|
|
"qps_list": [2],
|
|
"server_parameters": {
|
|
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
|
"tensor_parallel_size": 4,
|
|
"speculative_config": {
|
|
"model": "turboderp/Qwama-0.5B-Instruct",
|
|
"num_speculative_tokens": 4,
|
|
"draft_tensor_parallel_size": 1
|
|
}
|
|
},
|
|
"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
|
|
}
|
|
}
|
|
]
|