mudler / mudler/vllm.cpp

feat: Pascal support

Open
#146 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
423
Forks
53
Avg merge
20h 26m
Merged PRs (30d)
310

Description

It would be nice to have support for the older cards even if parallelism doesn't work initially.
Of course the best would be if we could mismatch different arch cards and still get it working.

https://en.wikipedia.org/wiki/Pascal_(microarchitecture)

The target is sm_61(most cards), and sm_60(Tesla P100)

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 reading the linked Pascal microarchitecture reference and searching the repository for existing GPU architecture targets and support paths. Compare the current behavior with the requested sm_61 and sm_60 targets; done should be defined for Pascal cards, while mixed architectures and parallelism remain explicitly scoped.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.