ROCm / ROCm/FastFlowLM

KV cache in server mode?

Open
#486 14 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
1.9k
Forks
152
Avg merge
4h 14m
Merged PRs (30d)
11

Description

Good day,

Apparently from my understanding KV cache works only in CLI mode? Is there any plan to implement this in the future, like llama.cpp does?

Thank you for your attention.

Contributor guide

Open the contributing guide

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 locating the CLI and server execution paths and compare how KV caching is handled in each mode. Review the existing server request and inference flow, then use llama.cpp as the stated reference for expected behavior. Done means KV cache support is implemented for server mode with its behavior and limitations documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
backend, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.