1.7 KiB
type, title, description, tags, timestamp
| type | title | description | tags | timestamp | ||||
|---|---|---|---|---|---|---|---|---|
| benchmark plan | frank-default-large ubatch sweep | Standardized ubatch sweep for the active kingjones Qwen3.8 ROCmFPX deployment. |
|
2026-09-01 |
frank-default-large ubatch sweep
This benchmark uses the active frank-default-large model on Dankclaw with
llama-bench. It does not use llama-server, HTTP requests, or server-log
scraping. Stop the production service before running it and start the service
again afterward.
The old custom harnesses are retained in .AGENTTRASH/bench-scripts-20260901/
for auditability only. Their results are invalid and must not be used.
Sweep
The default points are 256, 512, 768, 1024, 1280, 1536, 2048, 3072, 4096, 5120, 6144. This implements the requested 256-step range through 1536 and
1024-step range from 2048 through 6144. Each point runs three 256-token decode
requests by default.
Run on Dankclaw from the repository checkout:
sudo systemctl stop frank-default-large
./scripts/bench-ubatch.sh
sudo systemctl start frank-default-large
The script uses the active Q6 AGENT model, a fixed 16K prompt workload, and
llama-bench JSONL output. The initial ubatch-only sweep is:
256, 512, 768, 1024, 1280, 1536, 1792, 2048, 3072, 4096, 5120, 6144
The GPU is shared with live workloads; do not run with the production service up.
Results
No valid results are recorded here. All results from the retired custom
harnesses are explicitly discarded. Record the raw llama-bench JSONL output
from the new harness here after a clean run.