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

server: continue to update other slots on embedding concurrent request (#5699)

Browse source 
* server: #5655 - continue to update other slots on embedding concurrent request.

* server: tests: add multi users embeddings as fixed

* server: tests: adding OAI compatible embedding concurrent endpoint

* server: tests: adding OAI compatible embedding with multiple inputs
This commit is contained in:
Pierrick Hymbert 2024-02-24 19:16:04 +01:00 • committed by GitHub
parent 4c4cb30736
commit 9e359a4f47
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 168 additions and 78 deletions
Download patch file Download diff file Expand all files Collapse all files

46
examples/server/tests/features/parallel.feature
View file

@ -8,6 +8,7 @@ Feature: Parallel
And 42 as server seed
And 64 KV cache size
And 2 slots
And embeddings extraction
And continuous batching
Then the server is starting
Then the server is healthy
@ -75,3 +76,48 @@ Feature: Parallel
Then the server is busy
Then the server is idle
Then all prompts are predicted
Scenario: Multi users embeddings
Given a prompt:
"""
Write a very long story about AI.
"""
And a prompt:
"""
Write another very long music lyrics.
"""
And a prompt:
"""
Write a very long poem.
"""
And a prompt:
"""
Write a very long joke.
"""
Given concurrent embedding requests
Then the server is busy
Then the server is idle
Then all embeddings are generated
Scenario: Multi users OAI compatibility embeddings
Given a prompt:
"""
In which country Paris is located ?
"""
And a prompt:
"""
Is Madrid the capital of Spain ?
"""
And a prompt:
"""
What is the biggest US city ?
"""
And a prompt:
"""
What is the capital of Bulgaria ?
"""
And a model tinyllama-2
Given concurrent OAI embedding requests
Then the server is busy
Then the server is idle
Then all embeddings are generated