llama.cpp
[ggml-webgpu] Handle buffer overlap / buffer aliasing for concat operator
#24000
Merged
Merged
[ggml-webgpu] Handle buffer overlap / buffer aliasing for concat operator #24000
reeselevine
merged
22 commits into
ggml-org:master
from
nikhilJain17:nikhilJain17/concat-overlap
Merge
df604979
Merge
5ae7583c
merge
70238e02
Merge with master
9f9d0640
Merge
e93b40d0
Merge
52b381bb
merge with master
5904ae49
merge with master
ae076c0a
Merge
de413da9
Merge branch 'master' of https://github.com/nikhilJain17/llama.cpp
2c32cdc4
Merge branch 'master' of https://github.com/nikhilJain17/llama.cpp
19438c18
Only run webgpu CI on my fork
cf82d32b
Merge branch 'master' of https://github.com/nikhilJain17/llama.cpp
76662da3
Merge branch 'master' of https://github.com/nikhilJain17/llama.cpp
e92f013e
Add webgpu only workflow
931d5d15
Merge branch 'master' of https://github.com/nikhilJain17/llama.cpp
69bdd8dc
Merge branch 'master' of https://github.com/nikhilJain17/llama.cpp
bb6ed31c
fix
33763d72
handle buffer overlap case for concat operator
aae41cfd
restore build-webgpu.yml
8cb549fb
yomaytk
approved these changes
on 2026-06-02
Run clang-format
30d4bf3a
reeselevine
commented
on 2026-06-03
Update ggml/src/ggml-webgpu/wgsl-shaders/concat.wgsl
fd1d497d
reeselevine
approved these changes
on 2026-06-05
CISC
approved these changes
on 2026-06-05
Reviewers
Assignees
No one assigned
Labels
ggml
WebGPU
Milestone
No milestone
Login to write a write a comment.
Login via GitHub