llama.cpp
d55356d3 - cuda : mark I16 and I32 ops as unsupported

Commit

1 year ago

cuda : mark I16 and I32 ops as unsupported ggml-ci

References

#4750 - sync : ggml

Author

ggerganov

ggerganov

Committer

ggerganov

ggerganov

Parents

Loading