Speed test matrix
GLM-4.7-185B-W4A16 on CMP 170HX 64GB ×2
vllm · 0.32.0rc1.dev249+g18305948a · GPTQ W4A164 contexts (32K–184K) × 8 concurrency levels (1–128) · prefill at 8K, 32K, 64K
Hardware
- Type
- Discrete GPU
- GPU
- CMP 170HX
- GPU count
- 2
- VRAM
- 64 GB (2 × 32 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
- GPTQ W4A16
- 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. KV cache: int4_per_token_head. Layout: PP2 (stock vLLM flag) # 2x 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 0xSero/GLM-4.7-185B-W4A16 --max-model-len 202752 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code --pipeline-parallel-size 2 --kv-cache-dtype int4_per_token_head --attention-backend TRITON_ATTN
Prefill
prompt tok/s by context length8K context594.013,753 ms TTFT
32K context146.0220,553 ms TTFT
64K context136.0473,316 ms TTFT
Sustained decode
total tok/s · rows are context length, columns are simultaneous requests| Context | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128 |
|---|---|---|---|---|---|---|---|---|
| 32K | 14.7670 ms TTFT | 27.8887 ms TTFT | 31.31,508 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 9.41,090 ms TTFT | 18.01,531 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 128K | Failed | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 184K | Failed | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
Failed: requests to the server failed during 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 | 594.0 | — | 13,753 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 146.0 | — | 220,553 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 136.0 | — | 473,316 ms | — | — | 1 | — | — |
| Sustained decode | 32K | 1 | Valid | 14.7 | 14.7 | 670 ms | 68.0 ms | 1.0 | 0 | 440 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 27.8 | 13.8 | 887 ms | 72.2 ms | 2.0 | 0 | 833 | 30.0 s |
| Sustained decode | 32K | 4 | Valid | 31.3 | 7.9 | 1,508 ms | 127.2 ms | 4.0 | 0 | 940 | 30.0 s |
| 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 | 9.4 | 9.5 | 1,090 ms | 105.5 ms | 1.0 | 0 | 283 | 30.0 s |
| Sustained decode | 64K | 2 | Valid | 18.0 | 9.0 | 1,531 ms | 111.4 ms | 2.0 | 0 | 541 | 30.0 s |
| Sustained decode | 64K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | Failed | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 128K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | 184K | 1 | Failed | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 184K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 184K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 184K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 184K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 184K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 184K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 184K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Failed: requests to the server failed during this measurement. Over capacity: not run because this many requests at this context would exceed the server's KV cache.