Speed test matrix
Olmo-3.1-32B-Think on H200 NVL 141GB
vllm · 0.26.1rc1.dev638+g52be12cfa · BF164 contexts (8K–59K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 59K, 64K
Hardware
- Type
- Discrete GPU
- GPU
- H200 NVL
- VRAM
- 141 GB
- OS
- linux
Engine
- Engine
- vllm
- Version
- 0.26.1rc1.dev638+g52be12cfa
- Quantization
- BF16
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- cuda-13.2
- Commit
52be12cfac0c
Run
- Served model
- olmo
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.4.29
- Decode test
- Fixed duration
- Prefill mode
- Measured during decode warm-up
- Time per measurement
- 30 s
- Max output
- 4,096 tokens
Launch command
"$HOME/env_h200-allenai-vllm/bin/vllm" serve allenai/Olmo-3.1-32B-Think --served-model-name olmo --trust-remote-code --tensor-parallel-size 1 --max-model-len 65536 --gpu-memory-utilization 0.871691 --host 0.0.0.0 --port 8000 --api-key <redacted>
Prefill
prompt tok/s by context length8K context8,490636 ms TTFT
16K context8,0951,311 ms TTFT
32K context7,9152,658 ms TTFT
59K context7,6415,055 ms TTFT
64K context7,5465,551 ms TTFT
Sustained decode
total tok/s · rows are context length, columns are simultaneous requests| Context | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128 |
|---|---|---|---|---|---|---|---|---|
| 8K | 50.356 ms TTFT | 99.072 ms TTFT | 192.7107 ms TTFT | 364.8155 ms TTFT | 663.9228 ms TTFT | 1,120.6348 ms TTFT | 1,639.9480 ms TTFT | Over capacity |
| 16K | 50.075 ms TTFT | 98.691 ms TTFT | 190.8138 ms TTFT | 357.5205 ms TTFT | 638.2305 ms TTFT | 1,046.0348 ms TTFT | Over capacity | Over capacity |
| 32K | 49.687 ms TTFT | 97.5117 ms TTFT | 186.9195 ms TTFT | 344.6291 ms TTFT | 600.0437 ms TTFT | Over capacity | Over capacity | Over capacity |
| 59K | 48.9118 ms TTFT | 95.4177 ms TTFT | 180.8250 ms TTFT | 325.0366 ms TTFT | 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 | 8,490.0 | — | 636 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 8,095.0 | — | 1,311 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 7,915.0 | — | 2,658 ms | — | — | 1 | — | — |
| Prefill | 59K | 1 | Valid | 7,641.0 | — | 5,055 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 7,546.0 | — | 5,551 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 50.3 | 50.3 | 56 ms | 19.9 ms | 1.0 | 0 | 1,508 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 99.0 | 49.6 | 72 ms | 20.2 ms | 2.0 | 0 | 2,970 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 192.7 | 48.2 | 107 ms | 20.7 ms | 4.0 | 0 | 5,780 | 30.0 s |
| Sustained decode | 8K | 8 | Valid | 364.8 | 45.6 | 155 ms | 21.9 ms | 8.0 | 0 | 10,936 | 30.0 s |
| Sustained decode | 8K | 16 | Valid | 663.9 | 41.6 | 228 ms | 24.0 ms | 16.0 | 0 | 19,904 | 30.0 s |
| Sustained decode | 8K | 32 | Valid | 1,120.6 | 35.2 | 348 ms | 28.4 ms | 32.0 | 0 | 33,600 | 30.0 s |
| Sustained decode | 8K | 64 | Valid | 1,639.9 | 25.8 | 480 ms | 38.8 ms | 64.0 | 0 | 49,152 | 30.0 s |
| Sustained decode | 8K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Valid | 50.0 | 50.0 | 75 ms | 20.0 ms | 1.0 | 0 | 1,500 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 98.6 | 49.3 | 91 ms | 20.3 ms | 2.0 | 0 | 2,958 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 190.8 | 47.7 | 138 ms | 21.0 ms | 4.0 | 0 | 5,724 | 30.0 s |
| Sustained decode | 16K | 8 | Valid | 357.5 | 44.7 | 205 ms | 22.4 ms | 8.0 | 0 | 10,720 | 30.0 s |
| Sustained decode | 16K | 16 | Valid | 638.2 | 40.0 | 305 ms | 25.0 ms | 16.0 | 0 | 19,152 | 30.0 s |
| Sustained decode | 16K | 32 | Valid | 1,046.0 | 32.8 | 348 ms | 30.5 ms | 32.0 | 0 | 31,360 | 30.0 s |
| Sustained decode | 16K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 1 | Valid | 49.6 | 49.6 | 87 ms | 20.2 ms | 1.0 | 0 | 1,488 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 97.5 | 48.8 | 117 ms | 20.5 ms | 2.0 | 0 | 2,924 | 30.0 s |
| Sustained decode | 32K | 4 | Valid | 186.9 | 46.8 | 195 ms | 21.4 ms | 4.0 | 0 | 5,604 | 30.0 s |
| Sustained decode | 32K | 8 | Valid | 344.6 | 43.1 | 291 ms | 23.2 ms | 8.0 | 0 | 10,336 | 30.0 s |
| Sustained decode | 32K | 16 | Valid | 600.0 | 37.6 | 437 ms | 26.6 ms | 16.0 | 0 | 18,000 | 30.0 s |
| Sustained decode | 32K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 59K | 1 | Valid | 48.9 | 48.9 | 118 ms | 20.4 ms | 1.0 | 0 | 1,467 | 30.0 s |
| Sustained decode | 59K | 2 | Valid | 95.4 | 47.7 | 177 ms | 20.9 ms | 2.0 | 0 | 2,862 | 30.0 s |
| Sustained decode | 59K | 4 | Valid | 180.8 | 45.2 | 250 ms | 22.1 ms | 4.0 | 0 | 5,424 | 30.0 s |
| Sustained decode | 59K | 8 | Valid | 325.0 | 40.6 | 366 ms | 24.6 ms | 8.0 | 0 | 9,752 | 30.0 s |
| Sustained decode | 59K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 59K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 59K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 59K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.