Prefix caching on a hybrid model, one H100: Qwen3.8-27B FP8, vLLM 0.31.0, chat-like traffic
Quick-mode measurement on one H100 SXM on RunPod Secure Cloud (November 5, 2026): Qwen3.8-27B FP8, a hybrid model (48 Gated DeltaNet and 16 full-attention layers), on vLLM 0.31.0 with default automatic prefix caching (mamba cache mode 'align', 784-token cache blocks with the default BF16 KV cache), --max-num-seqs 512, text-only, chat-like workload (median 1,024 input / 256 output tokens). The same SLO search ran four times with 0%, 50%, 75% and 90% of every prompt drawn from eight shared prefixes; cache hit rates are vLLM's own prefix-cache counters (0.0%, 21.1%, 40.8%, 55.6%). Capacity within p99 TTFT ≤ 2 s and p99 TPOT ≤ 50 ms rose from 3.43 to 5.83 requests per second. No accuracy gate (random-token prompts); the model answered a smoke-test question correctly at each start.
Results
Each value is the median of 2 runs.
SLO goodput
Tokens per joule
Decode bandwidth utilization
Not measured in this report.
GPU board power
GPU board power only — excludes CPUs, memory, NICs, fans and PSU losses.
All numbers
Cards for equal goodput = 64 × reference goodput ÷ configuration goodput, rounded up.
| Metric | No prompt reuse (0% cache hits) | 50% shared prefix (21.1% cache hits) | 75% shared prefix (40.8% cache hits) | 90% shared prefix (55.6% cache hits) |
|---|---|---|---|---|
| Engine build | vllm 0.31.0 · KV BF16 | vllm 0.31.0 · KV BF16 | vllm 0.31.0 · KV BF16 | vllm 0.31.0 · KV BF16 |
| Decode bandwidth utilization (MBU) | — | — | — | — |
| GPU board power | 0.61 kW | 0.61 kW | 0.61 kW | 0.64 kW |
| SLO goodput | 1,379 tok/s | 1,631 tok/s | 1,872 tok/s | 2,309 tok/s |
| Tokens per joule | 2.27 | 2.65 | 3.05 | 3.59 |
| TTFT p99 | 946 ms | 699 ms | 530 ms | 558 ms |
| TPOT p99 | 45.9 ms | 47.0 ms | 45.8 ms | 48.2 ms |
| SLO met | yes | yes | yes | yes |
| Accuracy (none) | — | — | — | — |
| Accuracy Δ vs. reference | — | — | — | — |
| Cards for equal goodput | 64 | 55 | 48 | 39 |
Setup
Any change to these fields makes it a different report.
- Accelerator
- 1× NVIDIA H100 80GB HBM3
- Rated HBM BW
- 3.35 TB/s per GPU
- Driver / runtime
- 595.91.07
- Host
- RunPod Secure Cloud 1x H100 SXM 80GB (US-MO-1, pod h4dvtjc8j7mu7e)
- Engine
- vllm 0.31.0
- Kernel libraries
- vllm/vllm-openai:v0.31.0 --max-model-len 32768 --max-num-seqs 512 --language-model-only --enable-prompt-tokens-details
- Model
- Qwen3.8-27B-FP8 (?)
- Quantization
- FP8 weights, BF16 KV cache
- Parallelism
- 1 replica × TP1
- Workload trace
- chat-mix-v1
- Input tokens
- median 1,024 · p90 4,096
- Output tokens
- median 256 · p90 1,024
- Arrival
- Poisson, rate swept to SLO boundary
- Power source
- GPU board power sum (NVIDIA) · 1 Hz · 120 s steady state
- Runs per config
- 2 (variance band ±1.2%)
- Accuracy gate
- none · max drop 0.5 pts
Not covered
Do not extrapolate this report to the following.
- Whole-node power (no BMC access on this host)
- Quick mode: short windows, few repeats
- Synthetic shared prefixes (8-prefix pool, random tokens)
- Accuracy: no accuracy gate was run
Reproduce
Run on the same hardware and software versions. Results should fall within ±1.2%.
tokenwatt run --spec h100-hyb-bf16-chat-prefix-cache.spec.yaml --label 'hyb-bf16-chat-0' --role other --out runs/hyb-bf16-chat-0.json tokenwatt run --spec h100-hyb-bf16-chat-prefix-cache.spec.yaml --label 'hyb-bf16-chat-0.5' --role other --out runs/hyb-bf16-chat-0-5.json tokenwatt run --spec h100-hyb-bf16-chat-prefix-cache.spec.yaml --label 'hyb-bf16-chat-0.75' --role other --out runs/hyb-bf16-chat-0-75.json tokenwatt run --spec h100-hyb-bf16-chat-prefix-cache.spec.yaml --label 'hyb-bf16-chat-0.9' --role other --out runs/hyb-bf16-chat-0-9.json tokenwatt report runs/hyb-bf16-chat-0.json runs/hyb-bf16-chat-0-5.json runs/hyb-bf16-chat-0-75.json runs/hyb-bf16-chat-0-9.json --title 'Prefix caching on a hybrid model, one H100: Qwen3.8-27B FP8, vLLM 0.31.0, chat-like traffic'