如何在 Linux 的 Dell Pro Max 16 Plus 搭配 Qualcomm 推斷卡上使用 vLLM 執行效能指標

Summary: 瞭解如何使用 vLLM 在 Dell Pro Max 16 Plus 上搭配 Linux 的 Qualcomm Inference Card 執行效能指標測試。

Instructions

Affected Products

This article applies to This article does not apply to This article is not tied to any specific product. Not all product versions are identified in this article.

Check out other resources

Instructions

下載 Qualcomm Program Container （QPC）。
從 Zentree 的預編譯模型目錄下載預構建的 AI 模型 QPC - 用於雲 AI 加速器的 Zentree-Qualcomm 預編譯模型目錄

注意：尋找以下內容，以確保 QPC 與 Dell Pro Max 相容 SoCs / Tensor slicing = 2
```
tar -xzvf ~/Downloads/qpc_name.tar.gz
```
使用 vLLM 提供大型語言模型（LLM）。
開啟 終端機 並執行下列命令（替換 <QPC_DIR>小 <MODEL_ID>小 <CTX_LEN>小 <BATCH_SIZE>以及 <PREFILL_SEQ_LEN>)。
注意：那 <MODEL_ID>小 <CTX_LEN>小 <BATCH_SIZE>以及 <PREFILL_SEQ_LEN> 取決於 QPC 編譯配置。對於由 Zentree 構建和託管的 QPC，這些值會記錄在其網站上。映射是 <BATCH_SIZE> 與「完整批量大小」， <CTX_LEN> 與「上下文長度（CL）」，以及 <PREFILL_SEQ_LEN> 與 Zentree 型號 QPC 組態表中的「分塊提示長度」。另請注意，某些模型需要設置 Huggingface 令牌，您需要將其傳遞到容器中才能訪問。
```
    docker run --rm -it \

    --name qaic-bench

    --device=/dev/accel/accel1 \

    --device=/dev/accel/accel2 \

    --network host \

    --ulimit nofile=1048576 \

    -e OMP_NUM_THREADS=8 \

    -e HF_TOKEN=$HF_TOKEN \

    -v ~/Downloads/<QPC_DIR>:/root/qpc \

    ghcr.io/quic/cloud_ai_inference_ubuntu24:1.20.6.0 \

    /opt/vllm-env/bin/vllm serve <MODEL_ID> \

    --max-num-seq <BATCH_SIZE> \

    --max-model-len <CTX_LEN> \

    --max-seq_len-to-capture <PREFILL_SEQ_LEN> \

    --device qaic \

    --device-group 0,1 \

    --quantization mxfp6 \

    --kv-cache-dtype mxint8 \

    --override-qaic-config "qpc_path=/root/qpc/qpc"
```
注意：所有 Zentree 託管的 Dell Pro Max 適用 QPC 的建置方式 num_devices=2，但是如果使用構建模型 num_devices=1，則 --device-group 應設為 0 或 1。

所有 Zentree 託管的 Dell Pro Max 適用 QPC 的建置方式 mxfp6_matmul=true，但是如果使用構建模型 mxfp6_matmul=false，則 --quantization mxfp6 應該被刪除。

所有 Zentree 託管的 Dell Pro Max 適用 QPC 的建置方式 mxint8_kv_cache=true，但是如果使用構建模型 mxint8_kv_cache=false，則 --kv-cache-dtype mxint8 應該被刪除。

看到消息“應用程式啟動完成”後，表示模型已準備好進行推理。

若要停止 vLLM （因此卸載模型並關閉容器），請在此終端機視窗中按下 Ctrl+C。較大的機型可能需要 1 分鐘才能卸下。

參考資料：Docker - Qualcomm Cloud AI SDK 使用者指南和 vLLM - Qualcomm Cloud AI SDK 使用者指南

執行基準測試。
開啟新 終端機 並執行下列命令（替換 <MODEL_ID> 和 <BATCH_SIZE> 以匹配步驟 2 中提供的模型）。的值 num-prompts小 random-input-len以及 random-output-len 可以根據需要進行調整。


    docker exec -it qaic-bench \

    /opt/vllm-env/bin/vllm bench serve \

    --model  \

    --num-prompts 25 \

    --max-concurrency  \

    --random-input-len 256 \

    --random-output-len 256

效能指標完成後，vLLM 會列印產生的指標。

注意：要僅獲取解碼（令牌生成）階段（不包括預填充（提示處理）階段的輸送量（令牌/秒或 TPS），可以使用 1000 ÷平均 TPOT （ms）計算 TPS。

例如，20 毫秒的平均 TPOT 相當於每秒 50 個令牌（TPS）的解碼輸送量。

工作範例：

下載 Qwen3-30B-A3B-Instruct-2507 預先製作的 QPC。
對於本劇本，我們使用預構建的QPC用於 Qwen3 30B A3B Instruct 2507

。
有 2 個預構建模型可用於支援 2 個 SoC 的 AI100 推理卡 - 一個具有 4K 環境長度，另一個具有 8K 上下文長度。本 Playbook 使用 2 SoC、4K 上下文長度模型。
請按照以下步驟從存檔中下載並提取QPC。請注意，如果您尚未安裝 curl，則可以使用以下命令在終端中安裝它（sudo apt install curl)。


        # Use existing Downloads folder for model downloads

        cd ~/Downloads

        # Download QPC archive from Zentree as qwen3-30b-a3b-instruct-2507.tar.gz

        curl -fSL https://dc00tk1pxen80.cloudfront.net/SDK1.20.4/Qwen/Qwen3-30B-A3B-Instruct-2507/

        Qwen3-30B-A3B-Instruct-2507_qpc_16cores_1pl_4096cl_1bs_2devices_mxfp6_mxint8.tar.gz -o qwen3-30b-a3b-instruct-2507.tar.gz

        # Extract QPC archive

        tar -xzvf qwen3-30b-a3b-instruct-2507.tar.gz

        # Rename extracted directory to qwen3-30b-a3b-instruct-2507-qpc

        mv $(tar -tzf qwen3-30b-a3b-instruct-2507.tar.gz | head -1 | cut -f1 -d"/") qwen3-30b-a3b-instruct-2507-qpc

使用 vLLM 供應 Qwen3：30B 機型。
開啟 終端機 並執行下列命令。從上面的一般食譜中注意 <QPC_DIR> 使用「-v ~/Downloads/qwen3-30b-a3b-instruct-2507-qpc:/root/qpc」行到模型下載到的 QPC 目錄， <MODEL_ID> 映射到”Qwen/Qwen3-30B-A3B-Instruct-2507," <CTX_LEN> 映射到 4096， <BATCH_SIZE> 映射到 1，並且 <PREFILL_SEQ_LEN> 映射到 1（全部來自使用 4K 上下文長度的 Qwen3：30B 模型的 Zentree 模型頁面）。

請注意，如果您以前沒有使用過此版本的 AI100 Docker 容器，則在打開 Docker 容器之前會獲取 ~14GB。
```
        docker run --rm -it \

        --name qaic-bench \

        --device=/dev/accel/accel1 \

        --device=/dev/accel/accel2 \

        --network host \

        --ulimit nofile=1048576 \

        -e OMP_NUM_THREADS=8 \

        -v ~/Downloads/qwen3-30b-a3b-instruct-2507-qpc:/root/qpc \

        ghcr.io/quic/cloud_ai_inference_ubuntu24:1.20.6.0 \

        /opt/vllm-env/bin/vllm serve Qwen/Qwen3-30B-A3B-Instruct-2507 \

        --max-num-seq 1 \

        --max-model-len 4096 \

        --max-seq_len-to-capture 1 \

        --device qaic \

        --device-group 0,1 \

        --quantization mxfp6 \

        --kv-cache-dtype mxint8 \

        --override-qaic-config "qpc_path=/root/qpc/qpc"
```
模型已準備好進行推理，一旦您看到消息”Application startup complete.」

注意：若要停止 vLLM （卸載模型並關閉容器），請在此終端機視窗中按下 Ctrl+C。較大的機型可能需要 1 分鐘才能卸下。

參考資料：Docker - Qualcomm Cloud AI SDK 使用者指南和 vLLM - Qualcomm Cloud AI SDK 使用者指南

執行基準測試。
開啟新 終端機 並執行下列命令（替換 <MODEL_ID> 對於 --model 和 <BATCH_SIZE> 對於 --max-concurrency 以匹配步驟 2 中提供的模型）。的值 num-prompts小 random-input-len以及 random-output-len 可以根據需要進行調整。


        docker exec -it qaic-bench \

        /opt/vllm-env/bin/vllm bench serve \

        --model Qwen/Qwen3-30B-A3B-Instruct-2507 \

        --num-prompts 25 \

        --max-concurrency 1 \

        --random-input-len 256 \

        --random-output-len 256

範例輸出擷取。
使用 vLLM 服務 Qwen3：30B 的輸出範例。
vLLM 的範例輸出：


        dell@dell:~/Downloads/qwen3-30b-a3b-instruct-2507-qpc$ docker run --rm -it \

        --name qaic-bench \

        --device=/dev/accel/accel1 \

        --device=/dev/accel/accel2 \

        --network host \

        --ulimit nofile=1048576 \

        -e OMP_NUM_THREADS=8 \

        -v ~/Downloads/qwen3-30b-a3b-instruct-2507-qpc:/root/qpc \

        ghcr.io/quic/cloud_ai_inference_ubuntu24:1.20.6.0 \

        /opt/vllm-env/bin/vllm serve Qwen/Qwen3-30B-A3B-Instruct-2507 \

        --max-num-seq 1 \

        --max-model-len 4096 \

        --max-seq_len-to-capture 1 \

        --device qaic \

        --device-group 0,1 \

        --quantization mxfp6 \

        --kv-cache-dtype mxint8 \

        --override-qaic-config "qpc_path=/root/qpc/qpc"

        loading /opt/qti-aic/dev/lib/x86_64/libQAic.so

        INFO 01-15 17:46:28 [__init__.py:269] Automatically detected platform qaic.


        
        INFO 01-15 17:46:30 [api_server.py:1043] vLLM API server version 0.8.6.dev0+gba41cc90e.d20251229



        INFO 01-15 17:46:30 [api_server.py:1044] args: Namespace(subparser='serve', model_tag='Qwen/Qwen3-30B-A3B-Instruct-2507', config='', host=None, port=8000, uvicorn_log_level='info', disable_uvicorn_access_log=False, allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, chat_template=None, chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, enable_ssl_refresh=False, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, tool_call_parser=None, tool_parser_plugin='', model='Qwen/Qwen3-30B-A3B-Instruct-2507', task='auto', tokenizer=None, hf_config_path=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, allowed_local_media_path=None, load_format='auto', download_dir=None, model_loader_extra_config={}, use_tqdm_on_load=True, config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', max_model_len=4096, guided_decoding_backend='auto', reasoning_parser=None, logits_processor_pattern=None, model_impl='auto', distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=1, data_parallel_size=1, enable_expert_parallel=False, max_parallel_loading_workers=None, ray_workers_use_nsight=False, disable_custom_all_reduce=False, block_size=None, gpu_memory_utilization=0.9, swap_space=4, kv_cache_dtype='mxint8', num_gpu_blocks_override=None, enable_prefix_caching=None, prefix_caching_hash_algo='builtin', cpu_offload_gb=0, calculate_kv_scales=False, disable_sliding_window=False, use_v2_block_manager=True, seed=None, max_logprobs=20, disable_log_stats=False, quantization='mxfp6', rope_scaling=None, rope_theta=None, hf_token=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=1, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config={}, limit_mm_per_prompt={}, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=None, enable_lora_bias=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=None, max_prompt_adapters=1, max_prompt_adapter_token=0, device='qaic', speculative_config=None, ignore_patterns=[], served_model_name=None, qlora_adapter_name_or_path=None, show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, max_num_batched_tokens=None, max_num_seqs=1, max_num_partial_prefills=1, max_long_partial_prefills=1, long_prefill_token_threshold=0, num_lookahead_slots=0, scheduler_delay_factor=0.0, preemption_mode=None, num_scheduler_steps=1, multi_step_stream_outputs=True, scheduling_policy='fcfs', enable_chunked_prefill=None, disable_chunked_mm_input=False, scheduler_cls='vllm.core.scheduler.Scheduler', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', worker_extension_cls='', generation_config='auto', override_generation_config=None, enable_sleep_mode=False, additional_config=None, enable_reasoning=False, disable_cascade_attn=False, override_qaic_config={'qpc_path': '/root/qpc/qpc'}, device_group=[0, 1], disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, enable_server_load_tracking=False, dispatch_function=<function ServeSubcommand.cmd at 0x7416f976a710>)




        config.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 963/963 [00:00<00:00, 6.38MB/s]


        
        INFO 01-15 17:46:34 [config.py:728] This model supports multiple tasks: {'score', 'generate', 'classify', 'embed', 'reward'}. Defaulting to 'generate'.



        WARNING 01-15 17:46:34 [arg_utils.py:1711] --kv-cache-dtype is not supported by the V1 Engine. Falling back to V0.


        
        INFO 01-15 17:46:34 [config.py:1415] Using fp8 data type to store kv cache. It reduces the GPU memory footprint and boosts the performance. Meanwhile, it may cause accuracy drop without a proper scaling factor


        
        INFO 01-15 17:46:34 [config.py:1820] Disabled the custom all-reduce kernel because it is not supported on current platform.


        
        config_1m.json: 77.3kB [00:00, 163MB/s]


        
        generation_config.json: 100%|██████████████████████████████████████████████████████████████████████████████████████| 239/239 [00:00<00:00, 2.47MB/s]


        
        model.safetensors.index.json: 1.70MB [00:00, 57.5MB/s]


        
        tokenizer.json: 100%|██████████████████████████████████████████████████████████████████████████████████████████| 11.4M/11.4M [00:02<00:00, 5.23MB/s]


        
        tokenizer_config.json: 9.38kB [00:00, 41.9MB/s]


        
        vocab.json: 2.78MB [00:00, 25.4MB/s]


        
        INFO 01-15 17:46:38 [api_server.py:246] Started engine process with PID 51


        
        merges.txt: 1.67MB [00:00, 11.8MB/s]


        
        loading /opt/qti-aic/dev/lib/x86_64/libQAic.so


        
        INFO 01-15 17:46:40 [__init__.py:269] Automatically detected platform qaic.



        INFO 01-15 17:46:41 [llm_engine.py:247] Initializing a V0 LLM engine (v0.8.6.dev0+gba41cc90e.d20251229) with config: model='Qwen/Qwen3-30B-A3B-Instruct-2507', speculative_config=None, tokenizer='Qwen/Qwen3-30B-A3B-Instruct-2507', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=4096, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=True, quantization=mxfp6, enforce_eager=False, kv_cache_dtype=mxint8,  device_config=cpu, decoding_config=DecodingConfig(guided_decoding_backend='auto', reasoning_backend=None), observability_config=ObservabilityConfig(show_hidden_metrics=False, otlp_traces_endpoint=None, collect_model_forward_time=False, collect_model_execute_time=False), seed=None, served_model_name=Qwen/Qwen3-30B-A3B-Instruct-2507, num_scheduler_steps=1, multi_step_stream_outputs=True, enable_prefix_caching=None, chunked_prefill_enabled=False, use_async_output_proc=False, disable_mm_preprocessor_cache=False, mm_processor_kwargs=None, pooler_config=None, compilation_config={"splitting_ops":[],"compile_sizes":[],"cudagraph_capture_sizes":[1],"max_capture_size":1}, use_cached_outputs=True,



        WARNING 01-15 17:46:42 [qaic.py:100] Pin memory is not supported on Qaic.



        WARNING 01-15 17:46:42 [registry.py:217] Model class <class 'vllm.model_executor.models.mllama.MllamaForConditionalGeneration'> already has a multi-modal processor registered to <vllm.multimodal.registry.MultiModalRegistry object at 0x7f2ffb2ddc90>. It is overwritten by the new one.



        WARNING 01-15 17:46:42 [registry.py:217] Model class <class 'vllm.model_executor.models.mllama4.Llama4ForConditionalGeneration'> already has a multi-modal processor registered to <vllm.multimodal.registry.MultiModalRegistry object at 0x7f2ffb2ddc90>. It is overwritten by the new one.



        WARNING 01-15 17:46:42 [qaic_worker.py:102] Reducing Torch parallelism from 8 threads to 8 to avoid unnecessary CPU contention. Set VLLM_QAIC_MAX_CPU_THREADS to tune this value as needed.



        INFO 01-15 17:46:42 [qaic_worker.py:87] Setting RLIMIT_STACK to 16.0MB.


        
        INFO 01-15 17:46:44 [parallel_state.py:1004] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, TP rank 0


        
        loading /opt/qti-aic/dev/lib/x86_64/libQAic.so


        
        INFO 01-15 17:46:44 [executor_base.py:112] # qaic blocks: 1, # CPU blocks: 0


        
        INFO 01-15 17:46:44 [executor_base.py:117] Maximum concurrency for 4096 tokens per request: 1.00x


        
        {'prefill_seq_len': 1, 'ctx_len': 4096, 'batch_size': 1, 'full_batch_size': 1, 'device_group': [0, 1], 'num_devices': 2, 'num_cores': 16, 'mxfp6_matmul': True, 'mxint8_kv_cache': True, 'aic_enable_depth_first': True, 'prefill_only': None, 'compile_only': False}



        INFO 01-15 17:46:44 [qaic.py:959] Using qpc:-/root/qpc/qpc


        
        Stages:  1


        
        INFO 01-15 17:46:44 [qserve_model_runner.py:66] Loading QPC...


        
        INFO 01-15 17:46:44 [qserve_model_runner.py:67] This may take some time, please don't press CTRL-C during this phase...



        INFO 01-15 17:46:52 [qserve_model_runner.py:88] Successfully loaded QPC in 7.791425864999837 secs



        WARNING 01-15 17:46:52 [qserve_model_runner.py:122] User entered `include_sampler`=True. But the provided QPC is not compiled to run sampling on the QAIC device. Falling back to the PyTorch backend.


        
        INFO 01-15 17:46:52 [qserve_model_runner.py:162] Warming-up with Dummy run...


        
        INFO 01-15 17:46:52 [qserve_model_runner.py:178] Successfully finished Dummy run in 0.04556767500025671 secs


        
        INFO 01-15 17:46:52 [llm_engine.py:444] init engine (profile, create kv cache, warmup model) took 7.86 seconds


        
        WARNING 01-15 17:46:53 [config.py:1251] Default sampling parameters have been overridden by the model's Hugging Face generation config recommended from the model creator. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`.


        
        INFO 01-15 17:46:53 [serving_chat.py:124] Using default chat sampling params from model: {'temperature': 0.7, 'top_k': 20, 'top_p': 0.8}


        
        INFO 01-15 17:46:53 [serving_completion.py:61] Using default completion sampling params from model: {'temperature': 0.7, 'top_k': 20, 'top_p': 0.8}


        
        INFO 01-15 17:46:53 [api_server.py:1090] Starting vLLM API server on http://0.0.0.0:8000


        
        INFO 01-15 17:46:53 [launcher.py:28] Available routes are:


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /openapi.json, Methods: GET, HEAD


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /docs, Methods: GET, HEAD


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /docs/oauth2-redirect, Methods: GET, HEAD


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /redoc, Methods: GET, HEAD


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /health, Methods: GET


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /load, Methods: GET


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /ping, Methods: POST, GET


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /tokenize, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /detokenize, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /v1/models, Methods: GET



        INFO 01-15 17:46:53 [launcher.py:36] Route: /version, Methods: GET


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /v1/chat/completions, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /v1/completions, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /v1/embeddings, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /pooling, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /score, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /v1/score, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /v1/audio/transcriptions, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /rerank, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /v1/rerank, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /v2/rerank, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /invocations, Methods: POST


        
        INFO 01-15 17:46:53 [launcher.py:36] Route: /metrics, Methods: GET


        
        INFO:     Started server process [1]


        
        INFO:     Waiting for application startup.


        
        INFO:     Application startup complete.

QAIC-bench 的基準測試輸出範例。

QAC-bench 的範例輸出


        dell@dell:~$ docker exec -it qaic-bench \

        /opt/vllm-env/bin/vllm bench serve \

        --model Qwen/Qwen3-30B-A3B-Instruct-2507 \

        --num-prompts 25 \

        --max-concurrency 1 \

        --random-input-len 256 \

        --random-output-len 256



        loading /opt/qti-aic/dev/lib/x86_64/libQAic.so


        
        INFO 01-15 17:47:44 [__init__.py:269] Automatically detected platform qaic.



        Namespace(subparser='bench', bench_type='serve', dispatch_function=<function BenchmarkServingSubcommand.cmd at 0x71abbd45e9e0>, endpoint_type='openai-comp', label=None, base_url=None, host='127.0.0.1', port=8000, endpoint='/v1/completions', dataset_name='random', max_concurrency=1, model='Qwen/Qwen3-30B-A3B-Instruct-2507', tokenizer=None, best_of=1, use_beam_search=False, num_prompts=25, logprobs=None, request_rate=inf, burstiness=1.0, seed=0, trust_remote_code=False, disable_tqdm=False, profile=False, save_result=False, metadata=None, result_dir=None, result_filename=None, ignore_eos=False, percentile_metrics='ttft,tpot,itl', metric_percentiles='99', goodput=None, random_input_len=256, random_output_len=256, random_range_ratio=1.0, random_prefix_len=0, tokenizer_mode='auto', served_model_name=None, lora_modules=None)



        Starting initial single prompt test run...


        
        Initial test run completed. Starting main benchmark run...


        
        Traffic request rate: inf


        
        Burstiness factor: 1.0 (Poisson process)


        
        Maximum request concurrency: 1



        100%|████████████████████████████████████████████████████████████████████████████████████| 25/25 [05:00<00:00, 12.02s/it]



        ============ Serving Benchmark Result ============

        Successful requests:                     25        

        Benchmark duration (s):                  300.53    

        Total input tokens:                      6400      

        Total generated tokens:                  6400      

        Request throughput (req/s):              0.08      

        Output token throughput (tok/s):         21.30     

        Total Token throughput (tok/s):          42.59     

        ---------------Time to First Token----------------

        Mean TTFT (ms):                          5915.88   

        Median TTFT (ms):                        5803.64   

        P99 TTFT (ms):                           7153.97   

        -----Time per Output Token (excl. 1st token)------

        Mean TPOT (ms):                          23.94     

        Median TPOT (ms):                        23.82     

        P99 TPOT (ms):                           25.18     

        ---------------Inter-token Latency----------------

        Mean ITL (ms):                           23.94     

        Median ITL (ms):                         23.78     

        P99 ITL (ms):                            25.77     

        ==================================================

        dell@dell:~$

要計算輸出生成的令牌的 TPS（令牌/秒）結果，請使用 1000 ÷平均值 TPOT（上面的 23.94）= 41.8 TPS。

回到頁首

Affected Products

Dell Pro Max 16 Plus MB16250

Article Number: 000446730

Article Type: How To

Last Modified: 24 May 2026

Version: 5

Check if your device is covered by Support Services.

如何在 Linux 的 Dell Pro Max 16 Plus 搭配 Qualcomm 推斷卡上使用 vLLM 執行效能指標

Summary: 瞭解如何使用 vLLM 在 Dell Pro Max 16 Plus 上搭配 Linux 的 Qualcomm Inference Card 執行效能指標測試。

Instructions

Affected Products

Instructions

Affected Products

Article Properties

Find answers to your questions from other Dell users

Support Services

Article Properties

Find answers to your questions from other Dell users

Support Services

如何在 Linux 的 Dell Pro Max 16 Plus 搭配 Qualcomm 推斷卡上使用 vLLM 執行效能指標

Summary: 瞭解如何使用 vLLM 在 Dell Pro Max 16 Plus 上搭配 Linux 的 Qualcomm Inference Card 執行效能指標測試。

Detailed Article

Instructions

Affected Products

Instructions

Affected Products

Article Properties

Find answers to your questions from other Dell users

Support Services

Article Properties

Find answers to your questions from other Dell users

Support Services