microsoft / microsoft/vattention

why init_kvcache need vattention.reserve_physical_pages(GPU_MEM_RESERVE)

Open
#13 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C
Stars
523
Forks
46
Avg merge
9h 23m
Merged PRs (30d)
1

Description

I believe this is similar to how vLLM reserves actual resources at startup. According to the paper, no actual resources should be allocated at startup; the CUDA interface should only be invoked to allocate resources when processing inference requests.
image

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

The payload names no files or tests; start by tracing init_kvcache to vattention.reserve_physical_pages(GPU_MEM_RESERVE) and the CUDA allocation path. Compare this startup behavior with the paper's request-time allocation model, then establish the expected behavior and add coverage for the initialization and inference-request paths.

Written by the indexing model from the issue text.

Assessment

Tech stack
c
Domain
ai-infra-agents
Issue type
Refactor
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.