llama.cpp
6e9007ae - ggml-webgpu: improve i-quants mul_mat performance and speed up prefill (#24530)

Commit

38 days ago

ggml-webgpu: improve i-quants mul_mat performance and speed up prefill (#24530) * Improve prefill speeds for i-quants * Fix #if defined() usage in preprocessor guards.

References

#24530 - ggml-webgpu: improve i-quants mul_mat performance and speed up prefill

Author

yomaytk

Parents

dd4623a7

llama.cpp 6e9007ae - ggml-webgpu: improve i-quants mul_mat performance and speed up prefill (#24530)

llama.cpp
6e9007ae - ggml-webgpu: improve i-quants mul_mat performance and speed up prefill (#24530)