dank/serverAppConfigs
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

Raise ubatch benchmark context to 32K

Browse Source
This commit is contained in:
Frank
2026-08-25 17:44:45 -07:00
parent 4cb67d7b33
commit 96f5ae6fe1
3 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/LLM/ubatch-benchmark-large.md
+2 -2
View File
@@ -13,7 +13,7 @@ timestamp: 2026-09-01
# frank-default-large ubatch sweep
This benchmark sweeps the active `frank-default-large` model on Dankclaw using
scratch ports and a 16K-context workload. The production service is stopped
scratch ports and a 32K-context workload. The production service is stopped
before the sweep and restarted by the benchmark's exit handler.
## Sweep
@@ -30,7 +30,7 @@ STOPSVC=1 ./scripts/bench-ubatch-rocmi4.sh
```
The script uses the active Q6 AGENT model, standalone MTP draft, a fixed
16K batch, and the tracked Sharp
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.