CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-07 09:57:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : update per-seq context computation

Browse Source
This commit is contained in:
Georgi Gerganov
2025-10-23 17:54:53 +03:00
parent db6f8e24e6
commit 8e11ec8eee
8 changed files with 40 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tools/server/tests/unit/test_infill.py
View File

@@ -18,7 +18,7 @@ def test_infill_without_input_extra():
"input_suffix": "}\n",
})
assert res.status_code == 200
assert match_regex("(Ann|small|shiny|Daddy)+", res.body["content"])
assert match_regex("(Ann|small|shiny|Daddy|Jimmy)+", res.body["content"])
def test_infill_with_input_extra():
@@ -34,7 +34,7 @@ def test_infill_with_input_extra():
"input_suffix": "}\n",
})
assert res.status_code == 200
assert match_regex("(Dad|excited|park)+", res.body["content"])
assert match_regex("(Dad|excited|park|Jimmy)+", res.body["content"])
@pytest.mark.parametrize("input_extra", [