serverAppConfigs/docs/LLM/ubatch-benchmark-large.md

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.	llama.cpp rocm benchmark ubatch	2026-09-01

frank-default-large ubatch sweep

This benchmark sweeps the active frank-default-large model on Dankclaw using scratch ports and a 32K-context workload. The production service is stopped before the sweep and restarted by the benchmark's exit handler.

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:

STOPSVC=1 ./scripts/bench-ubatch-rocmi4.sh

The script uses the active Q6 AGENT model, standalone MTP draft, a fixed 32K batch, and the tracked Sharp template, and --reasoning-format deepseek. It reports server timing lines and per-run generation throughput. Run only when the production service can be interrupted; the GPU is shared with live workloads.

Results

Record results below after the sweep, including failures or OOM points.

ubatch	prefill	generation	notes
256	—	—	pending
512	—	—	pending
768	—	—	pending
1024	—	—	pending
1280	—	—	pending
1536	—	—	pending
2048	—	—	pending
3072	—	—	pending
4096	—	—	pending
5120	—	—	pending
6144	—	—	pending

See also

• LLM fleet index
• Deployment
• Active kingjones runbook