minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

[Spec][Ngram] 4/N: Remove max_match_window_size and min_match_window_size, matching all suffixes of the Trie (#21225)

Browse Source
This commit is contained in:
Khoa Pham
2026-04-01 22:09:46 -07:00
committed by GitHub
parent 269589ad71
commit f836658077
13 changed files with 46 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/test/runners.py
+1 -8
View File
@@ -574,8 +574,6 @@ class SRTRunner:
speculative_num_steps: Optional[int] = None,
speculative_eagle_topk: Optional[int] = None,
speculative_num_draft_tokens: Optional[int] = None,
speculative_ngram_min_match_window_size: Optional[int] = None,
speculative_ngram_max_match_window_size: Optional[int] = None,
disable_overlap_schedule: bool = False,
disable_custom_all_reduce: bool = False,
torchao_config: Optional[str] = None,
@@ -606,12 +604,7 @@ class SRTRunner:
spec_kwargs["speculative_num_draft_tokens"] = speculative_num_draft_tokens
elif speculative_algorithm == "NGRAM":
spec_kwargs["speculative_algorithm"] = speculative_algorithm
spec_kwargs["speculative_ngram_min_match_window_size"] = (
speculative_ngram_min_match_window_size
)
spec_kwargs["speculative_ngram_max_match_window_size"] = (
speculative_ngram_max_match_window_size
)
spec_kwargs["speculative_num_draft_tokens"] = speculative_num_draft_tokens
self.engine = Engine(
model_path=model_path,