From f25bf86065b65aeb213c6dc1f0565b32922d14af Mon Sep 17 00:00:00 2001 From: Liangsheng Yin Date: Wed, 1 Apr 2026 22:18:24 -0700 Subject: [PATCH] Fix ngram doc for speculative_num_draft_tokens default (#21910) --- docs/advanced_features/speculative_decoding.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/advanced_features/speculative_decoding.md b/docs/advanced_features/speculative_decoding.md index b8fe2d890..9806f244e 100644 --- a/docs/advanced_features/speculative_decoding.md +++ b/docs/advanced_features/speculative_decoding.md @@ -387,7 +387,7 @@ Enable it with: | Parameter | Description | Default | |---|---|---| -| `--speculative-num-draft-tokens` | Number of draft tokens verified per step. If omitted, defaults to `min(--speculative-ngram-max-trie-depth, 12)`. | `12` (with default ngram settings) | +| `--speculative-num-draft-tokens` | Number of draft tokens verified per step. | `12` | | `--speculative-ngram-min-bfs-breadth` | Minimum BFS breadth. | `1` | | `--speculative-ngram-max-bfs-breadth` | Maximum BFS breadth. | `10` | | `--speculative-ngram-match-type` | Ngram tree-building mode: `"BFS"` for recency-based expansion or `"PROB"` for frequency-based expansion. | `"BFS"` |