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

server: tests: add --model-url tests

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-03-16 18:15:20 +01:00
parent 545fef6e0e
commit 4fadb072e9
3 changed files with 19 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/tests/README.md
View file

@ -57,7 +57,7 @@ Feature or Scenario must be annotated with `@llama.cpp` to be included in the de
To run a scenario annotated with `@bug`, start: To run a scenario annotated with `@bug`, start:
```shell ```shell
DEBUG=ON ./tests.sh --no-skipped --tags bug DEBUG=ON ./tests.sh --no-skipped --tags bug --stop
``` ```
After changing logic in `steps.py`, ensure that `@bug` and `@wrong_usage` scenario are updated. After changing logic in `steps.py`, ensure that `@bug` and `@wrong_usage` scenario are updated.

3
examples/server/tests/features/embeddings.feature
View file

@ -4,7 +4,8 @@ Feature: llama.cpp server
Background: Server startup Background: Server startup
Given a server listening on localhost:8080 Given a server listening on localhost:8080
And a model file bert-bge-small/ggml-model-f16.gguf from HF repo ggml-org/models And a model url https://huggingface.co/ggml-org/models/resolve/main/bert-bge-small/ggml-model-f16.gguf
And a model file /tmp/ggml-model-f16.gguf
And a model alias bert-bge-small And a model alias bert-bge-small
And 42 as server seed And 42 as server seed
And 2 slots And 2 slots

17
examples/server/tests/features/steps/steps.py
View file

@ -32,6 +32,8 @@ def step_server_config(context, server_fqdn, server_port):
context.base_url = f'http://{context.server_fqdn}:{context.server_port}' context.base_url = f'http://{context.server_fqdn}:{context.server_port}'
context.model_alias = None context.model_alias = None
context.model_file = None
context.model_url = None
context.n_batch = None context.n_batch = None
context.n_ubatch = None context.n_ubatch = None
context.n_ctx = None context.n_ctx = None
@ -65,6 +67,16 @@ def step_download_hf_model(context, hf_file, hf_repo):
print(f"model file: {context.model_file}\n") print(f"model file: {context.model_file}\n")
@step('a model file {model_file}')
def step_model_file(context, model_file):
context.model_file = model_file
@step('a model url {model_url}')
def step_model_url(context, model_url):
context.model_url = model_url
@step('a model alias {model_alias}') @step('a model alias {model_alias}')
def step_model_alias(context, model_alias): def step_model_alias(context, model_alias):
context.model_alias = model_alias context.model_alias = model_alias
@ -1038,8 +1050,11 @@ def start_server_background(context):
server_args = [ server_args = [
'--host', server_listen_addr, '--host', server_listen_addr,
'--port', context.server_port, '--port', context.server_port,
'--model', context.model_file
] ]
if context.model_file:
server_args.extend(['--model', context.model_file])
if context.model_url:
server_args.extend(['--model-url', context.model_url])
if context.n_batch: if context.n_batch:
server_args.extend(['--batch-size', context.n_batch]) server_args.extend(['--batch-size', context.n_batch])
if context.n_ubatch: if context.n_ubatch: