Speed test matrix
Hy-MT2-30B-A3B-FP8 on CMP 170HX 64GB
vllm · 0.32.0rc1.dev249+g18305948a · FP86 contexts (0–248K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K, 128K
Hardware
- Type
- Discrete GPU
- GPU
- CMP 170HX
- VRAM
- 64 GB
- CPU
- 2x Intel Xeon E5-2630 v3
- RAM
- 64 GB
- OS
- Ubuntu 26.04.1
Engine
- Engine
- vllm
- Version
- 0.32.0rc1.dev249+g18305948a
- Quantization
- FP8
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- ghcr.io/morrowmake/vllm-cmp170hx@sha256:5b45c4d6feafefe2eba962375b0a9a0b64fd22b9e05abb4d1966f14a32a2db79
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 # 1x NVIDIA CMP 170HX 64GB (cmpunlocker), 180 W limit, PCIe Gen2 x4 | 2x Intel Xeon E5-2630 v3 | 64 GB DDR4 | Ubuntu 26.04.1, NVIDIA driver 610.57.04 | vLLM: Morrowmake vllm-cmp170hx image vllm serve tencent/Hy-MT2-30B-A3B-FP8 --max-model-len 262144 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code
Prefill
prompt tok/s by context length8K context7,8091,042 ms TTFT
16K context6,1962,600 ms TTFT
32K context4,6426,911 ms TTFT
64K context3,04121,051 ms TTFT
128K context1,79071,431 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 | 124.072 ms TTFT | 200.6108 ms TTFT | 320.5117 ms TTFT | 515.2128 ms TTFT | 780.7190 ms TTFT | 1,258.7380 ms TTFT | Over capacity | Over capacity |
| 16K | Looped | 166.6202 ms TTFT | Looped | 338.8498 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 93.7278 ms TTFT | 139.1366 ms TTFT | Looped | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 74.8415 ms TTFT | 103.6583 ms TTFT | Looped | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 128K | Looped | Looped | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 248K | 34.1Requests queued1,790 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
Requests queued: the server could not run all requests at once, so some waited in a queue. Looped: the model kept repeating the same text, so the benchmark discarded this measurement. 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 | 7,809.0 | — | 1,042 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 6,196.0 | — | 2,600 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 4,642.0 | — | 6,911 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 3,041.0 | — | 21,051 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 1,790.0 | — | 71,431 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 124.0 | 124.6 | 72 ms | 8.0 ms | 1.0 | 0 | 3,720 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 200.6 | 101.1 | 108 ms | 9.9 ms | 2.0 | 0 | 6,018 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 320.5 | 81.0 | 117 ms | 12.4 ms | 4.0 | 0 | 9,612 | 30.0 s |
| Sustained decode | 0 | 8 | Valid | 515.2 | 65.4 | 128 ms | 15.3 ms | 8.0 | 0 | 15,458 | 30.0 s |
| Sustained decode | 0 | 16 | Valid | 780.7 | 49.8 | 190 ms | 20.1 ms | 16.0 | 0 | 23,440 | 30.0 s |
| Sustained decode | 0 | 32 | Valid | 1,258.7 | 40.3 | 380 ms | 24.8 ms | 32.0 | 0 | 37,761 | 30.0 s |
| Sustained decode | 0 | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 2 | Valid | 166.6 | 92.5 | 202 ms | 10.9 ms | 2.0 | 0 | 4,996 | 30.0 s |
| Sustained decode | 16K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 8 | Valid | 338.8 | 42.5 | 498 ms | 23.5 ms | 8.0 | 0 | 10,160 | 30.0 s |
| 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 | 93.7 | 94.0 | 278 ms | 10.6 ms | 1.0 | 0 | 2,810 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 139.1 | 91.1 | 366 ms | 11.6 ms | 2.0 | 0 | 4,172 | 30.0 s |
| Sustained decode | 32K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| 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 | 64K | 1 | Valid | 74.8 | 75.0 | 415 ms | 13.3 ms | 1.0 | 0 | 2,243 | 30.0 s |
| Sustained decode | 64K | 2 | Valid | 103.6 | 1044.6 | 583 ms | 9.8 ms | 2.0 | 0 | 3,108 | 30.0 s |
| Sustained decode | 64K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 128K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 128K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 1 | Requests queued | 34.1 | 35.6 | 1,790 ms | 28.1 ms | 0.9 | 0 | 1,022 | 30.0 s |
| Sustained decode | 248K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 248K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Requests queued: the server could not run all requests at once, so some waited in a queue. Looped: the model kept repeating the same text, so the benchmark discarded this measurement. Over capacity: not run because this many requests at this context would exceed the server's KV cache.