llama.cpp
7a2db1a0 - ggml-webgpu: add support for f16 repeat (#26307)

Commit

5 days ago

ggml-webgpu: add support for f16 repeat (#26307)

References

#26307 - ggml-webgpu: fix minimax-m3 crash on webgpu by adding F16 REPEAT

Author

yomaytk

yomaytk

Parents

Loading