vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update issues.feature

Browse source
This commit is contained in:
GangT 2024-02-27 14:27:36 +07:00 • committed by GitHub
parent cbbd1efa06
commit a402d3cf74
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 13 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

14
examples/server/tests/features/issues.feature
View file

@ -1,4 +1,16 @@
# List of ongoing issues # List of ongoing issues
@bug @bug
Feature: Issues Feature: Issues llama.cpp server
# No confirmed issue at the moment # No confirmed issue at the moment
Background: Server startup
Given a server listening on localhost:8080
And a model with n_embed=4096
And n_ctx=32768
And 8 slots
And embeddings extraction
Then the server is starting
Then the server is healthy
Scenario: Embedding
When 8 identical inputs (1000 tokens) are computed simultaneously.
Then embeddings are generated, but they are different