LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend about wasmedge HOT 12 CLOSED

Week 1 update

• Using neural-speed repo to replace Intel Extension for Transformers to implement model calculate part.
• Spent time understanding wasi-nn code in wasmedge and wasmedge-wasi-nn

from wasmedge.

Week 2 update

• Successfully embed neural speed python code on C++ program
• Create new backend struct in wasmedge-wasi-nn

from wasmedge.

Week 3 update

• Spent time understanding Wasmedge Wasi-NN test process.
• Built a small unit test for neural speed backend.

from wasmedge.

Week 4 update

• Spent time tracing Wasmedge GGML implement.
• Add model download script.

from wasmedge.

Week 5 update

• Finish implement neural speed backend using Python interpreter.

from wasmedge.

Week 6 update

• Finish wasi-nn implement
• Finish easy example

from wasmedge.

Week 7 update

• Add install tutorial
• Improve neural speed backend

from wasmedge.

Week 8 update

• Improve neural speed backend
• Add simple benchmark between neural speed and llama.cpp

from wasmedge.

Week 9 update

• Improve neural speed backend
• Fix compile error on Windows platform

from wasmedge.

Hi @grorge123
Since all PRs are merged, should we close this issue? If so, please write down all the links of the merged PRs here, thanks.

from wasmedge.

Merged PR: #3303

from wasmedge.

This is resolved. Thanks @grorge123

from wasmedge.