cyberes
/
local-llm-server
Archived
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases 1 Wiki Activity

Merge cluster to master #3

Merged
cyberes merged 163 commits from cluster into master 2023-10-27 19:19:22 -06:00
Conversation 0 Commits 163 Files Changed 91 +2 -3
2 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 6723dd79dc - Show all commits

2
llm_server/routes/ooba_request_handler.py
View File

@ -16,7 +16,7 @@ class OobaRequestHandler(RequestHandler):
def handle_request(self, return_ok: bool = True): def handle_request(self, return_ok: bool = True):
assert not self.used assert not self.used
if self.offline: if self.offline:
msg = f'{self.selected_model} is not a valid model choice.' msg = 'The model you requested is not a valid choice. Please retry your query.'
print(msg) print(msg)
self.handle_error(msg) self.handle_error(msg)

3
server.py
View File

@ -1,5 +1,3 @@
from llm_server.routes.queue import priority_queue
try: try:
import gevent.monkey import gevent.monkey
@ -26,6 +24,7 @@ from llm_server.routes.server_error import handle_server_error
from llm_server.routes.v1 import bp from llm_server.routes.v1 import bp
from llm_server.sock import init_socketio from llm_server.sock import init_socketio
# TODO: return an `error: True`, error code, and error message rather than just a formatted message
# TODO: what happens when all backends are offline? What about the "online" key in the stats page? # TODO: what happens when all backends are offline? What about the "online" key in the stats page?
# TODO: redis SCAN vs KEYS?? # TODO: redis SCAN vs KEYS??
# TODO: implement blind RRD controlled via header and only used when there is a queue on the primary backend(s) # TODO: implement blind RRD controlled via header and only used when there is a queue on the primary backend(s)