-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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
feat: add SchedulerV3 #1996
feat: add SchedulerV3 #1996
Conversation
OlivierDehaene
commented
Jun 3, 2024
•
edited
Loading
edited
- Refactor code to allow supporting multiple versions of the generate.proto at the same time
- Add v3/generate.proto (ISO to generate.proto for now but allow for future changes without impacting v2 backends)
- Add Schedule trait to abstract queuing and batching mechanisms that will be different in the future
- Add SchedulerV2/V3 impl
7007390
to
8a820d8
Compare
message Input { | ||
repeated InputChunk chunks = 1; | ||
} | ||
|
||
enum GrammarType { | ||
GRAMMAR_TYPE_NONE = 0; | ||
GRAMMAR_TYPE_JSON = 1; |
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.
Shouldn't this be moved to v2 ?
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.
No I added it to v3 directly to avoid any changes to v2.
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 meant the file generate.proto
|
||
(scheduler, health_ext, shard_info, max_batch_total_tokens) | ||
} | ||
Err(_) => { |
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.
What kind of error does connecting a v3 client to a v2 shard create ?
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.
ClientError::Connection("Server does not support v3 interface".to_string())
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.
LGTM
- Refactor code to allow supporting multiple versions of the generate.proto at the same time - Add v3/generate.proto (ISO to generate.proto for now but allow for future changes without impacting v2 backends) - Add Schedule trait to abstract queuing and batching mechanisms that will be different in the future - Add SchedulerV2/V3 impl