Arm support Compute with fp16
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
- Domain
- machine-learning, mobile-dev, performance
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
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from MegEngine/InferLLM
-
SG2042 服务器 make 出错 Open
Difficulty 4/5 3-5 days Newbie friendliness 30/100
-
无法加载模型bin或者guff模型 Open
Difficulty 4/5 3-5 days Newbie friendliness 25/100
-
有打算支持qwen吗 Open
Difficulty 5/5 Over a week Newbie friendliness 25/100
-
Difficulty 4/5 3-5 days Newbie friendliness 20/100
-
这个有windows的部署教程吗 Open
Difficulty 3/5 1-2 days Newbie friendliness 35/100
All issues in MegEngine/InferLLM
Similar issues
-
Difficulty 1/5 Under an hour Newbie friendliness 90/100
AXERA-TECH/ax-llm#77 ·
-
Difficulty 1/5 Under an hour Newbie friendliness 90/100
games-on-whales/wolf#509 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
-
bug-unconfirmed
Difficulty 2/5 1-3 hours Newbie friendliness 76/100