root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-13 04:00:16 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

account for both api and web browser requests

Browse Source
This commit is contained in:
VJHack 2024-09-12 21:44:52 -05:00
parent daf64fc4a9
commit cb13382136
3 changed files with 18 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
examples/server/server.cpp
View File

@ -2591,11 +2591,15 @@ int main(int argc, char ** argv) {
return false;
};
auto middleware_server_state = [&state](const httplib::Request &, httplib::Response & res) {
auto middleware_server_state = [&res_error, &state](const httplib::Request & req, httplib::Response & res) {
server_state current_state = state.load();
if (current_state == SERVER_STATE_LOADING_MODEL) {
res.set_content("<html><body>The model is loading. Please wait.<br/>The user interface will appear soon.</body></html>", "text/html; charset=utf-8");
res.status = 503;
if(req.path == "/"){
res.set_content("<html><body>The model is loading. Please wait.<br/>The user interface will appear soon.</body></html>", "text/html; charset=utf-8");
res.status = 503;
} else {
res_error(res, format_error_response("Loading model", ERROR_TYPE_UNAVAILABLE));
}
return false;
}
return true;

10
examples/server/tests/features/server.feature
View File

@ -105,8 +105,16 @@ Feature: llama.cpp server
Given first token is removed
Then tokens can be detokenized
Scenario: Tokenize with pieces
When tokenizing with pieces:
"""
What is the capital of Germany?
媽
"""
Then tokens are given with pieces
Scenario: Models available
Given available models
Then 1 models are supported
Then model 0 is identified by tinyllama-2
Then model 0 is trained on 128 tokens context
Then model 0 is trained on 128 tokens context

3
examples/server/tests/features/steps/steps.py
View File

@ -1208,6 +1208,7 @@ async def wait_for_slots_status(context,
while True:
async with await session.get(f'{base_url}/slots', params=params) as slots_response:
status_code = slots_response.status
print(await slots_response.text())
slots = await slots_response.json()
if context.debug:
print(f"slots responses {slots}\n")
@ -1372,4 +1373,4 @@ def start_server_background(context):
thread_stderr = threading.Thread(target=server_log, args=(context.server_process.stderr, sys.stderr))
thread_stderr.start()
print(f"server pid={context.server_process.pid}, behave pid={os.getpid()}")
print(f"server pid={context.server_process.pid}, behave pid={os.getpid()}")