llama.cpp
Add conv2d Implicit GEMM
#15805
Open

Add conv2d Implicit GEMM #15805

bssrdf wants to merge 9 commits into ggml-org:master from bssrdf:conv2d-implicit
bssrdf
bssrdf Add implicit GEMM convolution operation for 2D tensors in CUDA
8a589317
bssrdf Add implicit convolution support for 2D tensors in CPU and CUDA imple…
4d772873
bssrdf fix passing param as reference
3877608d
bssrdf Fix parameter order in conv2d_implicit and add comprehensive test cas…
6d84cbb5
bssrdf Fix boundary check in conv2d_implicit_kernel to include channel limits
5ffe97be
bssrdf bssrdf marked this pull request as draft 9 days ago
github-actions github-actions added testing
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
JohannesGaessler
bssrdf
leejet
bssrdf
leejet
JohannesGaessler
JohannesGaessler
JohannesGaessler commented on 2025-09-05
bssrdf Refactor conv2d_implicit_kernel for improved readability and consiste…
4b0f9d57
bssrdf Refactor conv2d_implicit_kernel for improved bitwise operations; add …
83a3b7d6
bssrdf merged with upstream master
735886b0
bssrdf Merge branch 'master' into conv2d-implicit
2ec76aa8
Green-Sky
bssrdf
Green-Sky
Green-Sky
bssrdf

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone