Add integration test for spec decode top k = 1 #3

yubofredwang · 2025-04-08T05:58:23Z

Motivation

Format your code according to the Code Formatting with Pre-Commit.
Add unit tests as outlined in the Running Unit Tests.
Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.

hebiao064 · 2025-04-08T06:00:23Z

test/srt/test_fa3.py

+                "--speculative-eagle-topk",
+                "1",
+                "--speculative-num-draft-tokens",
+                "4",


use 3, it need to be the same as --speculative-num-steps when we use topk = 1

trim

a566531

hebiao064 reviewed Apr 8, 2025

View reviewed changes

use 3 draft tokens

d01c6d7

hebiao064 merged commit 77d6ef4 into main Apr 8, 2025
0 of 2 checks passed