Speed test matrix
Step3-VL-10B on RTX 3090 24GB
vllm · 0.32.0 · BF164 contexts (0–56K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 56K
Hardware
- Type
- Discrete GPU
- GPU
- RTX 3090
- VRAM
- 24 GB
- CPU
- Intel Core i7-9700K (8C)
- RAM
- 32 GB
- OS
- Ubuntu 24.04.5
Engine
- Engine
- vllm
- Version
- 0.32.0
- Quantization
- BF16
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- vllm/vllm-openai:v0.32.0-x86_64
Run
- Served model
- bench
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.8.0
- Decode test
- Fixed duration
- Prefill mode
- Measured during decode warm-up
- Time per measurement
- 30 s
- Max output
- 8,192 tokens
Launch command
# Untuned out-of-the-box baseline. Spec decode: none. KV cache: fp8 # 1x RTX 3090 24GB (Zagitta/gpu-unlock), 420 W limit, PCIe Gen3 x16 | Intel Core i7-9700K 8C | 32 GB DDR4 | Ubuntu 24.04.5, NVIDIA driver 580.178.04 vllm serve stepfun-ai/Step3-VL-10B --max-model-len 65536 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code --language-model-only --kv-cache-dtype fp8
Prefill
prompt tok/s by context length8K context7,0331,173 ms TTFT
16K context6,0942,683 ms TTFT
32K context4,7686,827 ms TTFT
56K context3,55515,986 ms TTFT
Sustained decode
total tok/s · rows are context length, columns are simultaneous requests| Context | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128 |
|---|---|---|---|---|---|---|---|---|
| 0 | 51.833 ms TTFT | 103.533 ms TTFT | 204.255 ms TTFT | 398.959 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 48.368 ms TTFT | 96.2102 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 45.2103 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 56K | 41.4164 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.
TTFT is measured after the benchmark warms the server's prompt cache, so it mostly excludes prefill.
All measurements
Latencies are medians. Total tok/s is output across all simultaneous requests.| Phase | Context | Requests at once | Status | Total tok/s | Per request tok/s | TTFT | Time between tokens | Average active requests | Completed requests | Output tokens | Measured for |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Prefill | 8K | 1 | Valid | 7,033.0 | — | 1,173 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 6,094.0 | — | 2,683 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 4,768.0 | — | 6,827 ms | — | — | 1 | — | — |
| Prefill | 56K | 1 | Valid | 3,555.0 | — | 15,986 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 51.8 | 51.8 | 33 ms | 19.3 ms | 1.0 | 0 | 1,553 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 103.5 | 51.8 | 33 ms | 19.3 ms | 2.0 | 0 | 3,104 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 204.2 | 51.2 | 55 ms | 19.5 ms | 4.0 | 0 | 6,125 | 30.0 s |
| Sustained decode | 0 | 8 | Valid | 398.9 | 50.1 | 59 ms | 20.0 ms | 8.0 | 0 | 11,960 | 30.0 s |
| Sustained decode | 0 | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Valid | 48.3 | 48.3 | 68 ms | 20.7 ms | 1.0 | 0 | 1,447 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 96.2 | 48.2 | 102 ms | 20.8 ms | 2.0 | 0 | 2,886 | 30.0 s |
| Sustained decode | 16K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 1 | Valid | 45.2 | 45.3 | 103 ms | 22.1 ms | 1.0 | 0 | 1,357 | 30.0 s |
| Sustained decode | 32K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 1 | Valid | 41.4 | 41.5 | 164 ms | 24.1 ms | 1.0 | 0 | 1,242 | 30.0 s |
| Sustained decode | 56K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.