From d0ff6317cc28fe3aa0542c21294f7e23a3632241 Mon Sep 17 00:00:00 2001 From: Abhijith Jajam <129675815+jajamabhijith@users.noreply.github.com> Date: Thu, 29 Oct 2026 05:47:38 +0530 Subject: [PATCH] docs : fix DSpark confidence threshold flag name (--spec-draft-p-min) (#31178) --- docs/speculative.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/speculative.md b/docs/speculative.md index a32842a25..d8f3bcb39 100644 --- a/docs/speculative.md +++ b/docs/speculative.md @@ -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.