CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into gg/llama-kv-cache

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-01-29 15:01:26 +02:00
parent 918885697e f0d4b29edf
commit c30e34cdba
20 changed files with 331 additions and 136 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/tests/unit/test_completion.py
View File

@@ -87,7 +87,7 @@ def test_completion_stream_vs_non_stream():
assert content_stream == res_non_stream.body["content"]
def test_completion_stream_with_openai_library():
def test_completion_with_openai_library():
global server
server.start()
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1")
@@ -102,7 +102,7 @@ def test_completion_stream_with_openai_library():
assert match_regex("(going|bed)+", res.choices[0].text)
def test_completion_with_openai_library():
def test_completion_stream_with_openai_library():
global server
server.start()
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1")