120 lines
3.3 KiB
JSON
120 lines
3.3 KiB
JSON
{
|
|
"study_id": "dash0-qwen30b-a3b-community-vllm020-chat-0-8k-noharness",
|
|
"hardware": {
|
|
"gpu_count": 8,
|
|
"gpu_model": "H20",
|
|
"host_candidates": [
|
|
"dash0"
|
|
]
|
|
},
|
|
"model": {
|
|
"model_id": "Qwen/Qwen3-30B-A3B",
|
|
"served_model_name": "qwen3-30b-a3b-community"
|
|
},
|
|
"engine": {
|
|
"engine_name": "vllm",
|
|
"engine_version": "0.20.0",
|
|
"exec_path": "/tmp/wjh/venvs/vllm-0.20.0-cu129/bin/vllm",
|
|
"cwd": "/home/admin/cpfs/wjh/aituner/aituner",
|
|
"host": "127.0.0.1",
|
|
"port": 18231,
|
|
"healthcheck_path": "/v1/models",
|
|
"ready_timeout_s": 900,
|
|
"request_timeout_s": 900,
|
|
"launch_args": [
|
|
"serve",
|
|
"/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B"
|
|
],
|
|
"base_envs": {
|
|
"CUDA_VISIBLE_DEVICES": "0,1,2,3,4,5,6,7"
|
|
},
|
|
"base_flags": {
|
|
"host": "127.0.0.1",
|
|
"port": 18231,
|
|
"served-model-name": "qwen3-30b-a3b-community"
|
|
},
|
|
"tunable_envs": [],
|
|
"tunable_flags": [
|
|
"tensor-parallel-size",
|
|
"data-parallel-size",
|
|
"enable-expert-parallel",
|
|
"expert-parallel-size",
|
|
"gpu-memory-utilization",
|
|
"max-num-batched-tokens",
|
|
"max-num-seqs",
|
|
"block-size",
|
|
"enable-prefix-caching",
|
|
"enable-chunked-prefill"
|
|
],
|
|
"topology_constraints": {
|
|
"require_tp_dp_product_equals_gpu_count": false,
|
|
"require_ep_size_leq_tp_dp_product": true,
|
|
"require_ep_size_divides_tp_dp_product": true,
|
|
"require_enable_expert_parallel_when_ep_gt_one": true,
|
|
"validate_cuda_graph_sizes_divisible_by_tp_when_tp_ep_reduce_scatter": true,
|
|
"allowed_tp_dp_products": [1, 2, 4, 8],
|
|
"allowed_tensor_parallel_sizes": [1, 2, 4, 8],
|
|
"allowed_data_parallel_sizes": [1, 2, 4, 8],
|
|
"allowed_expert_parallel_sizes": [1, 2, 4, 8]
|
|
},
|
|
"python_executable": "/tmp/wjh/venvs/vllm-0.20.0-cu129/bin/python"
|
|
},
|
|
"trace": {
|
|
"windows_path": "/home/admin/cpfs/wjh/aituner/aituner/trace_windows/windows.json",
|
|
"window_id": "chat_w20260311_1000",
|
|
"u_field": "sampling_u",
|
|
"timestamp_field": "timestamp",
|
|
"max_concurrency": 64,
|
|
"input_length_filter": {
|
|
"min_input_tokens": 0,
|
|
"max_input_tokens": 8192
|
|
},
|
|
"max_requests_per_probe": 2048,
|
|
"replay_time_scale": 1.0,
|
|
"early_stop_max_lag_s": 120.0,
|
|
"early_stop_max_elapsed_s": 900.0
|
|
},
|
|
"slo": {
|
|
"target_pass_rate": 0.95,
|
|
"ttft_rule": {
|
|
"kind": "step_ms",
|
|
"buckets": [
|
|
{
|
|
"max_input_tokens": 4096,
|
|
"threshold_ms": 2000
|
|
},
|
|
{
|
|
"max_input_tokens": 32768,
|
|
"threshold_ms": 4000
|
|
},
|
|
{
|
|
"threshold_ms": 6000
|
|
}
|
|
]
|
|
},
|
|
"tpot_rule": {
|
|
"kind": "fixed_ms",
|
|
"threshold_ms": 50
|
|
}
|
|
},
|
|
"search": {
|
|
"low": 0.0,
|
|
"high": 0.125,
|
|
"tolerance": 0.001,
|
|
"max_probes": 6,
|
|
"sample_seed": 20260325
|
|
},
|
|
"llm": {
|
|
"system_prompt": "Tune community vLLM 0.20.0 serving for Qwen3-30B-A3B. Start from the default vLLM engine configuration, use only launch-safe patches, and optimize request_rate_per_gpu under the configured SLO.",
|
|
"max_history_trials": 8,
|
|
"use_harness": false,
|
|
"endpoint": {
|
|
"provider": "codex",
|
|
"model": "gpt-5.4",
|
|
"stream": true,
|
|
"api_key_env": "OPENAI_API_KEY",
|
|
"timeout_s": 240
|
|
}
|
|
}
|
|
}
|