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>
38 lines
926 B
JSON
38 lines
926 B
JSON
{
|
|
"defaults": {
|
|
"qps_list": [
|
|
"inf"
|
|
],
|
|
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
|
|
"server_environment_variables": {
|
|
"VLLM_RPC_TIMEOUT": 100000,
|
|
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120
|
|
},
|
|
"server_parameters": {
|
|
"dtype": "bfloat16",
|
|
"model": "openai/whisper-large-v3-turbo"
|
|
},
|
|
"client_parameters": {
|
|
"model": "openai/whisper-large-v3-turbo",
|
|
"backend": "openai-audio",
|
|
"endpoint": "/v1/audio/transcriptions",
|
|
"dataset_name": "hf",
|
|
"dataset_path": "openslr/librispeech_asr",
|
|
"hf_subset": "clean",
|
|
"hf_split": "test",
|
|
"no_stream": "",
|
|
"no_oversample": "",
|
|
"num_prompts": 200
|
|
}
|
|
},
|
|
"tests": [
|
|
{
|
|
"test_name": "serving_whisper_large_v3_turbo_librispeech_clean_tp1",
|
|
"server_parameters": {
|
|
"tensor_parallel_size": 1
|
|
},
|
|
"client_parameters": {}
|
|
}
|
|
]
|
|
}
|