-
Notifications
You must be signed in to change notification settings - Fork 243
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add new chat cli with auto backend feature #1276
Conversation
Hi @RunningLeon After the recent auto backend feature, there have been a few mishaps. For example, I compiled TurboMind using Python 3.9, so the turbomind.so is for Python 3.9. If I try to |
@zhyncs hi, thanks for your feedback. There is a warning for this case: Lines 42 to 50 in 8a2fed8
|
Hi @RunningLeon Yes, I did see this warning in source code, but in the actual usage process, seeing the warning did not attract attention. Should we consider raising the log level to error or as mentioned above, adding an option to force it off? |
Hi, @zhyncs |
@RunningLeon please add logs when fallback to pytorch engine
If turbomind is installed, but the model is not supported, there is no log to show the engine falllbacks to pytorch engine |
This case failed
|
f' Try to run with lmdeploy pytorch engine.') | ||
try_run_msg = (f'Try to run with pytorch engine because `{model_path}`' | ||
f' is not explicitly supported by lmdeploy. ') | ||
if is_turbomind_installed: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think these warning should only appear when user intent to use turbomind (for example, sending a turbomindconfig)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The default is using turbomind. Autobackend works only when backendconfig is None or TurbomindConfig.
Motivation
Support auto backend feature in chat cli
Modification
lmdeploy chat torch
andlmdeploy chat turbomind
intolmdeploy chat
command. Note the old commands still worklmdeploy chat
.BC-breaking (Optional)
No BC
Use cases (Optional)
pytorch backend
lmdeploy chat internlm/internlm-chat-7b --backend pytorch
turbomind
lmdeploy chat internlm/internlm-chat-7b
Checklist