Speed test matrix
Fara1.5-27B-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 prithivMLmods/Fara1.5-27B-FP8 --max-model-len 262144 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code --language-model-only
Prefill
prompt tok/s by context length8K context2,1253,832 ms TTFT
16K context2,0507,861 ms TTFT
32K context1,92416,674 ms TTFT
64K context1,68138,074 ms TTFT
128K context1,34395,244 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 | 34.3194 ms TTFT | 67.0299 ms TTFT | 130.1308 ms TTFT | 247.7497 ms TTFT | 473.4807 ms TTFT | 680.31,336 ms TTFT | Over capacity | Over capacity |
| 16K | 33.1422 ms TTFT | 63.3563 ms TTFT | 117.6888 ms TTFT | 207.61,522 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 32.0656 ms TTFT | 59.7908 ms TTFT | 106.71,436 ms TTFT | 177.32,460 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 30.1783 ms TTFT | 53.61,158 ms TTFT | 90.01,676 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 128K | 26.9964 ms TTFT | 44.41,204 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 248K | 21.1Requests queued2,706 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. 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 | 2,125.0 | — | 3,832 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 2,050.0 | — | 7,861 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 1,924.0 | — | 16,674 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 1,681.0 | — | 38,074 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 1,343.0 | — | 95,244 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 34.3 | 34.4 | 194 ms | 29.1 ms | 1.0 | 0 | 1,029 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 67.0 | 33.6 | 299 ms | 29.8 ms | 2.0 | 0 | 2,009 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 130.1 | 32.6 | 308 ms | 30.7 ms | 4.0 | 0 | 3,900 | 30.0 s |
| Sustained decode | 0 | 8 | Valid | 247.7 | 31.0 | 497 ms | 32.2 ms | 8.0 | 0 | 7,432 | 30.0 s |
| Sustained decode | 0 | 16 | Valid | 473.4 | 29.7 | 807 ms | 33.7 ms | 16.0 | 0 | 14,192 | 30.0 s |
| Sustained decode | 0 | 32 | Valid | 680.3 | 21.2 | 1,336 ms | 47.1 ms | 32.0 | 0 | 20,416 | 30.0 s |
| Sustained decode | 0 | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Valid | 33.1 | 33.1 | 422 ms | 30.2 ms | 1.0 | 0 | 993 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 63.3 | 31.5 | 563 ms | 31.7 ms | 2.0 | 0 | 1,898 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 117.6 | 29.1 | 888 ms | 34.4 ms | 4.0 | 0 | 3,528 | 30.0 s |
| Sustained decode | 16K | 8 | Valid | 207.6 | 25.3 | 1,522 ms | 39.5 ms | 8.0 | 0 | 6,224 | 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 | 32.0 | 32.1 | 656 ms | 31.2 ms | 1.0 | 0 | 960 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 59.7 | 29.7 | 908 ms | 33.7 ms | 2.0 | 0 | 1,790 | 30.0 s |
| Sustained decode | 32K | 4 | Valid | 106.7 | 26.2 | 1,436 ms | 38.1 ms | 4.0 | 0 | 3,200 | 30.0 s |
| Sustained decode | 32K | 8 | Valid | 177.3 | 21.2 | 2,460 ms | 47.2 ms | 8.0 | 0 | 5,312 | 30.0 s |
| 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 | 30.1 | 30.2 | 783 ms | 33.1 ms | 1.0 | 0 | 902 | 30.0 s |
| Sustained decode | 64K | 2 | Valid | 53.6 | 26.7 | 1,158 ms | 37.5 ms | 2.0 | 0 | 1,606 | 30.0 s |
| Sustained decode | 64K | 4 | Valid | 90.0 | 22.1 | 1,676 ms | 45.2 ms | 4.0 | 0 | 2,700 | 30.0 s |
| 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 | Valid | 26.9 | 27.0 | 964 ms | 37.0 ms | 1.0 | 0 | 807 | 30.0 s |
| Sustained decode | 128K | 2 | Valid | 44.4 | 22.3 | 1,204 ms | 44.9 ms | 2.0 | 0 | 1,332 | 30.0 s |
| 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 | 21.1 | 22.8 | 2,706 ms | 44.0 ms | 0.9 | 0 | 633 | 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. Over capacity: not run because this many requests at this context would exceed the server's KV cache.