zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-12-16 01:49:05 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Rename block sparse (#1149)

Browse Source 
* block_sparse_mm to gather_mm

* rename

* nit

* nit
This commit is contained in:
Awni Hannun
2024-05-22 07:48:34 -07:00
committed by GitHub
parent e6fecbb3e1
commit d568c7ee36
16 changed files with 120 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
mlx/backend/common/quantized.cpp
View File

@@ -357,7 +357,7 @@ void QuantizedMatmul::eval(const std::vector<array>& inputs, array& out) {
_qmm_dispatch(out, x, w, scales, biases, group_size_, bits_, transpose_);
}
void BlockSparseQMM::eval(const std::vector<array>& inputs, array& out) {
void GatherQMM::eval(const std::vector<array>& inputs, array& out) {
assert(inputs.size() == 6);
auto& x_pre = inputs[0];