microsoft / microsoft/vidur

Questions on CPU Overheads & KV Cache Aware Routing

Open
#63 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
682
Forks
128
Avg merge
9h 44m
Merged PRs (30d)
1

Description

Hi, thanks for open-sourcing this project!

I have a couple of questions:

  1. Regarding CPU overheads (e.g. scheduling, tokenization, etc) - while they’re mentioned in the documentation, from reading the code, it seems that a request can enter a batch immediately upon arrival. Does the simulator currently model these CPU-related delays? Also, the link in the docs appears to be broken.

  2. Are there any plans to continue developing new features in the simulator, such as KV cache-aware routing (like what's in NVIDIA's Dynamo KV Cache Routing?

Thanks!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by checking the documentation link and the simulator’s request-arrival and batching behavior to determine whether CPU-related delays are modeled. Then review the existing routing implementation and the referenced KV-cache routing design; the issue is complete only when the modeling status, documentation link, and future feature scope are clarified.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.