feat: Support HIP backend for the WASI-NN llama.cpp plugin on AMD platforms.
envgap__WasmEdge__WasmEdge-4037
01 / FAILURE SIGNATURE
As reported upstream
No identifying execution failure has been captured.
Not a benchmark task.
- In a clean container the reported failure did not reproduce, or the known fix did not make the project run.
02 / ENVIRONMENT RECIPE
- Base commit
702dd3c1d37b063086c46800ab2cdd7df1bae03b- Manifest
CMakeLists.txt- Reproduce
Awaiting issue-specific recipe- Run under trace
Awaiting a meaningful runtime command
03 / ORIGINAL ISSUE TEXT
WasmEdge/WasmEdge #4037 · read the original issue
### Summary Ref: https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#hip We would like to provide a series of the pre-built assets for the AMD platforms. ### Details * Add a new CMake option for the HIP build of the llama.cpp plugin. * Create a script to set up the environment for building. * Due to the lack of AMD devices, we are unable to verify the HIP behavior. * However, we should publish the pre-built assets for those who are interested in testing this plugin. ### Appendix _No response_
04 / LABELS
Labels from the report text only; not yet run
No supported category has been assigned.
Label rules and the text that matched
[]