MegEngine / MegEngine/InferLLM
Arm support Compute with fp16
Open
- Dominant language
- C++
- Stars
- 752
- Forks
- 94
- PR merge metrics
- No merged PRs in 30d
Description
Now Arm only support fp32 compute, fp16 compute will be fast on armv8.2 arch or above.
Contributor guide
No contributing guide indexed for this repository
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.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning, mobile-dev, performance
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100