Skip to content

[Feature]: Consider active requests and inflight tokens for saturation signal #320

Description

@jtechapps

Problem Statement

Currently saturation signals can be configured based on external metric which takes time to update because of the scrape interval this can lead to llm-d-async overshooting saturation. llm-d-async can also send a surge of requests before the saturation metric updates, and the async processor fetches it. This was seen in #304

Additionally not all inference requests have equal saturation impact on the server. For instance an inference request with (100000 input/1000 output tokens) will saturate the inference server's capacity signicantly more than a (500 input/100 output tokens) request. Currently in llm-d-async, both these request occupy a single queue and pool worker slot.

Proposed Solution

There are a few solutions that need to be experimented:

  1. See if latency-prediction sidecar can be utilized to predict impact on saturation
  2. add plugin support for request parsers to estimate token throughput.

Alternatives Considered

No response

Willingness to Contribute

Yes, I can submit a PR

Additional Context

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    Fields

    No fields configured for Epic.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions