happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

server : adjust spec tests to generate up to 16 tokens (#19093)

This commit is contained in:
Georgi Gerganov 2026-01-28 09:11:40 +02:00 committed by GitHub
parent c5c64f72ac
commit b931f81b5a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tools/server/tests/unit/test_speculative.py
View File

@ -30,6 +30,7 @@ def test_with_and_without_draft():
"prompt": "I believe the meaning of life is",
"temperature": 0.0,
"top_k": 1,
"n_predict": 16,
})
assert res.status_code == 200
content_no_draft = res.body["content"]
@ -42,6 +43,7 @@ def test_with_and_without_draft():
"prompt": "I believe the meaning of life is",
"temperature": 0.0,
"top_k": 1,
"n_predict": 16,
})
assert res.status_code == 200
content_draft = res.body["content"]
@ -68,6 +70,7 @@ def test_different_draft_min_draft_max():
"prompt": "I believe the meaning of life is",
"temperature": 0.0,
"top_k": 1,
"n_predict": 16,
})
assert res.status_code == 200
if last_content is not None: