llama.cpp
975221e9 - ggml : broadcast mul_mat + conv batch support (#2199)

Commit

2 years ago

ggml : broadcast mul_mat + conv batch support (#2199) * ggml : broadcast mul_mat + conv batch support * ggml : apply mul_mat broadcast fix by @jploski

References

#2199 - ggml : broadcast mul_mat + conv batch support

Author

ggerganov

Parents

4523d10d

llama.cpp 975221e9 - ggml : broadcast mul_mat + conv batch support (#2199)

llama.cpp
975221e9 - ggml : broadcast mul_mat + conv batch support (#2199)