RTX PRO 6000 Blackwell Server Edition · 96 GB
WeVisOne-VL-2B
Open a report for complete measurements.
- Task
- Text generation · Text → Text
- Workload
- 128K → 2K tokens · No cache reuse
- Concurrency
- 4 concurrent requests
- Format · Engine
- BF16 · vllm · vLLM 0.28.0
- Unit
- tok/s
- Mean throughput
- 66.8tok/s
- Observed GPU occupancy
- 85.3 GiB
- First token
- 15 s
- Reports combined
- 1
Launch this model
A compatible model launch executor has not been published yet.
Individual tests
Text → Text · Text generation · BF16 · vllm · 131072in-2048out · tok/s
Sortable table
Uncached prefill is unavailable when prompts reuse cache or reliable phase timings are missing. Open a report for its recorded phase timings and cache counts.
| Test date | Throughput | Concurrency / batch | P95 (s) | TTFT (ms) | Observed occupancy (GiB) | GPU power (W) | Decode (tok/s) | Uncached prefill (tok/s) | Parameters | View report |
|---|---|---|---|---|---|---|---|---|---|---|
| 10/26/2026, 12:51:38 AM | 66.75 tok/s | 4 | 144.628 | 15,049.25 | 85.25 | 461.58 | 19.04 | 13,548.15 | Parameters ↗ | 2c661c7e ↗ |
Recorded test parameters
Configuration 1 · Parameters
- model
- tencent/WeVisOne-VL-2B
- engine
- vllm
- quant
- BF16
- method
- wbench-search-http-v1
- task
- llm
- dataset
- migration-analysis-v1:sha256=68590c248e43f32c04dfd8062464fd1e4856917795fe307225e5c6112a54fe94:cache=isolated:repeats=3
- context
- 131072in-2048out
- input_tokens
- 131072
- output_tokens
- 2048
- duration
- 3600
- concurrency
- 4
- unit
- tok/s
- software
- { "kernel_selection": { "observed": { "attention_backends": [ "FLASH_ATTN" ], "cuda_graph_capture": [ "(EngineCore pid=6457) INFO 10-25 23:01:42 [model_runner.py:906] Graph capturing finished in 60 secs, took 0.39 GiB" ], "kv_cache_dtype": "auto", "linear_kernels": [], "max_num_batched_tokens": 8192, "scope": "Observed engine selections and graph capture; not per-layer dtype or peak-hardware-efficiency attestation", "source": "engine-startup-log" } }, "kv_capacity": { "gpu_cache_tokens": 732128, "maximum_concurrency": 5.48, "note": "Engine estimate, not measured saturation; hybrid cache token units may differ. Minimum reported worker bound.", "reference_tokens": 133632, "source": "vllm-startup-log" }, "packages": { "flash-attn": null, "flashinfer-python": "0.6.16.post3", "sgl-kernel": null, "sglang": null, "tokenizers": "0.23.3", "torch": "2.13.0", "transformers": "5.20.2", "triton": "3.7.1", "vllm": "0.28.0" }, "python_implementation": "cpython", "python_version": "3.12.3", "schema": "wbench.python-runtime.v1", "scope": "launch-environment-installed-distributions", "startup": { "context": 133632, "max_num_seqs": 256, "source": "suite-startup-settings" } }
- engine_provenance
- { "checkpoint_quantization": { "mixed_quantization": false, "quantized_weight_formats": null, "recipe_label": "BF16", "scope": "Declared quantized weight formats; unquantized modules and observed runtime kernels are separate evidence", "source": "checkpoint-metadata" }, "client_version": "1.1.71", "cpu_offload_gb": 0, "engine": "vllm", "gpu_driver_version": "580.82.07", "gpu_memory_utilization": 0.8999999761581421, "kernel_options": { "attention_backend": null, "humming_input_dtype": null, "kv_cache_dtype": null, "max_num_batched_tokens": null, "moe_backend": null }, "limit_mm_per_prompt": null, "model_config_sha256": "c50561386446ad7a1b2d61b662d25adfa399acbda713dd78eca8a9696c7e1bea", "model_revision": "798ffc7c87ad6104410812b589e240ba32d92315", "processor_config_sha256": "bfbc24af59a3e73a9cd0653b8d4ae758dfaec4e3e6c15dfb1c6c8ee8d5683c85", "reasoning_parser": null, "reported_cuda_version": "13.0", "runtime": { "kernel_selection": { "observed": { "attention_backends": [ "FLASH_ATTN" ], "cuda_graph_capture": [ "(EngineCore pid=6457) INFO 10-25 23:01:42 [model_runner.py:906] Graph capturing finished in 60 secs, took 0.39 GiB" ], "kv_cache_dtype": "auto", "linear_kernels": [], "max_num_batched_tokens": 8192, "scope": "Observed engine selections and graph capture; not per-layer dtype or peak-hardware-efficiency attestation", "source": "engine-startup-log" } }, "kv_capacity": { "gpu_cache_tokens": 732128, "maximum_concurrency": 5.48, "note": "Engine estimate, not measured saturation; hybrid cache token units may differ. Minimum reported worker bound.", "reference_tokens": 133632, "source": "vllm-startup-log" }, "packages": { "flash-attn": null, "flashinfer-python": "0.6.16.post3", "sgl-kernel": null, "sglang": null, "tokenizers": "0.23.3", "torch": "2.13.0", "transformers": "5.20.2", "triton": "3.7.1", "vllm": "0.28.0" }, "python_implementation": "cpython", "python_version": "3.12.3", "schema": "wbench.python-runtime.v1", "scope": "launch-environment-installed-distributions", "startup": { "context": 133632, "max_num_seqs": 256, "source": "suite-startup-settings" } }, "shared_gpu": false }
- kernel_settings
- —
- precision
- —
- resolution
- —
- performance_task
- { "id": "migration-analysis-v1", "prompt_sha256": "ff630a211c5eb70323b4ed5aed2a4725d7f699d5ad74915e0184c41a4e7ec96a", "sha256": "68590c248e43f32c04dfd8062464fd1e4856917795fe307225e5c6112a54fe94" }
- performance_scope
- —
- batch_size
- —
- dimensions
- —
- weight_quantization
- —
- max_sequence_length
- —
- model_scope
- —
- performance_dataset
- —
- workload_mode
- —
- graph_mode
- —
- model_revision
- —
- client_version
- 1.1.71