Han-Wen Tsao comments

Results 27 comments of


                                            Han-Wen Tsao

LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend

### Week 1 update - Using [neural-speed](https://github.com/intel/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

LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend

### Week 2 update - Successfully embed neural speed python code on C++ program - Create new backend struct in wasmedge-wasi-nn

LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend

### Week 3 update - Spent time understanding Wasmedge Wasi-NN test process. - Built a small unit test for neural speed backend.

LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend

### Week 4 update - Spent time tracing Wasmedge GGML implement. - Add model download script.

LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend

### Week 5 update - Finish implement neural speed backend using Python interpreter.

LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend

### Week 6 update - Finish wasi-nn implement - Finish easy example

LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend

### Week 7 update - Add install tutorial - Improve neural speed backend

LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend

### Week 8 update - Improve neural speed backend - Add simple benchmark between neural speed and llama.cpp

LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend

### Week 9 update - Improve neural speed backend - Fix compile error on Windows platform

LFX Workspace: Integrate Intel Extension for Transformers as a new WASI-NN backend

Merged PR: #3303