Files
ollama/cmd
Daniel Hiltgen e38b606e8b bench: add prompt calibration, context size flag, and NumCtx reporting
Add --num-ctx flag to set context size, and report NumCtx in model info
header. Calibrate tokens-per-word ratio during warmup using actual
tokenization metrics from the model, replacing the fixed 1.3 heuristic.
This produces more accurate prompt token counts for --prompt-tokens.

Also add fetchContextLength() to query running model context via /api/ps.
2026-04-01 15:20:37 -07:00
..
2025-02-13 17:09:26 -08:00
2026-03-26 18:06:53 -07:00
2026-03-25 16:37:02 -04:00
2024-08-01 17:06:06 -07:00
2024-06-04 11:13:30 -07:00