docs : fix DSpark confidence threshold flag name (--spec-draft-p-min) (#31178)

This commit is contained in:
Abhijith Jajam authored and GitHub committed 2026-10-29 08:17:38 +08:00
1 parent cf24317bea
commit d0ff6317cc
1 file changed
+3 -2
+3 -2
View File
@@ -100,8 +100,9 @@ llama-server -m Qwen3-4B.gguf -md Qwen3-4B-DSpark.gguf \
`--spec-draft-n-max` is clamped to the draft model's trained block size.
`--spec-draft-conf-min P` truncates each drafted block at the first position whose predicted
acceptance (from the draft's confidence head, if present) falls below `P` (default 0 = disabled).
`--spec-draft-p-min P` truncates each drafted block at the first position whose predicted
acceptance (from the draft's confidence head) falls below `P` (default 0 = disabled).
Values above 0 require a draft with a confidence head.
Currently only drafts with a Qwen3 backbone are supported; support for other backbones
(e.g. Gemma4) is planned.