chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[Spec][Ngram] 2/N: Rename branch length to max trie depth (#21181)

Browse Source 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
kpham-sgl
2026-03-22 23:35:25 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent d6b12c401c
commit bc4aaab6a1
11 changed files with 31 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/server_arguments.md
+1 -1
View File
@@ -299,7 +299,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
| `--speculative-ngram-min-bfs-breadth` | The minimum breadth for BFS (Breadth-First Search) in ngram speculative decoding. | `1` | Type: int |
| `--speculative-ngram-max-bfs-breadth` | The maximum breadth for BFS (Breadth-First Search) in ngram speculative decoding. | `10` | Type: int |
| `--speculative-ngram-match-type` | Ngram tree-building mode. `BFS` selects recency-based expansion and `PROB` selects frequency-based expansion. This setting is forwarded to the ngram cache implementation. | `BFS` | `BFS`, `PROB` |
| `--speculative-ngram-branch-length` | The branch length for ngram speculative decoding. | `18` | Type: int |
| `--speculative-ngram-max-trie-depth` | The max trie depth for ngram speculative decoding. | `18` | Type: int |
| `--speculative-ngram-capacity` | The cache capacity for ngram speculative decoding. | `10000000` | Type: int |
## Multi-layer Eagle speculative decoding