Arm support Compute with fp16

Open
#11 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
35/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Stale
Tech stack
cpp

Research direction

Start by locating the Arm-specific fp32 compute path and any architecture checks in the inference framework. Confirm how fp16 computation is selected on armv8.2 and newer, then verify inference behavior and performance while preserving support for older Arm targets.

Written by the indexing model from the issue text.

Description

Now Arm only support fp32 compute, fp16 compute will be fast on armv8.2 arch or above.

Dominant language
C++
Stars
752
Forks
94
PR merge metrics
No merged PRs in 30d

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.

More from MegEngine/InferLLM

All issues in MegEngine/InferLLM

Similar issues

More C++ issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.