Morph MORPH
SIGN IN SIGN UP
ggml-org / llama.cpp UNCLAIMED

LLM inference in C/C++

0 0 0 C++

ggml webgpu: faster matrix multiplication/matrix-vector multiplication (#17031)

* Faster tensors (#8)

Add fast matrix and matrix/vector multiplication.

* Use map for shader replacements instead of pair of strings
R
Reese Levine committed
647b960bd8017ee882d6633bc2e43e2ae82ee85c
Parent: 299f5d7
Committed by GitHub <noreply@github.com> on 11/8/2025, 3:27:20 AM