llama.cpp
Remove padding and multiple D2D copies for MTP
#24086
Merged

Remove padding and multiple D2D copies for MTP #24086

gaugarg-nv
github-actions github-actions added model
github-actions github-actions added testing
github-actions github-actions added Nvidia GPU
github-actions github-actions added Vulkan
github-actions github-actions added ggml
gaugarg-nv
ggerganov ggerganov assigned ggerganov ggerganov 73 days ago
ggerganov
ggerganov commented on 2026-06-09
github-actions github-actions added SYCL
github-actions github-actions added Apple Metal
github-actions github-actions added OpenCL
github-actions github-actions added Hexagon
github-actions github-actions added WebGPU
gaugarg-nv gaugarg-nv marked this pull request as ready for review 67 days ago
gaugarg-nv gaugarg-nv requested a review from CISC CISC 67 days ago
gaugarg-nv gaugarg-nv requested a review 67 days ago
gaugarg-nv gaugarg-nv requested a review 67 days ago
gaugarg-nv gaugarg-nv requested a review 67 days ago
gaugarg-nv gaugarg-nv requested a review 67 days ago
gaugarg-nv gaugarg-nv requested a review 67 days ago
gaugarg-nv gaugarg-nv requested a review 67 days ago
gaugarg-nv gaugarg-nv requested a review 67 days ago
gaugarg-nv gaugarg-nv requested a review from JohannesGaessler JohannesGaessler 67 days ago
gaugarg-nv
gaugarg-nv
gaugarg-nv commented on 2026-06-09
gaugarg-nv Make ggml_gated_delta_net take only the initial recurrent state (D, 1…
f3e880e6
gaugarg-nv Make GDN changes in all backends. Address review comments.
55fe676d
gaugarg-nv gaugarg-nv force pushed from 1f46cec1 to 55fe676d 67 days ago
gaugarg-nv Fix CI build errors
cf03efef
arthw
ggerganov
ggerganov approved these changes on 2026-06-10
ggerganov ggerganov added merge ready
gaugarg-nv
pwilkin
pwilkin approved these changes on 2026-06-10
gaugarg-nv gaugarg-nv merged e95dae18 into master 66 days ago
gaugarg-nv gaugarg-nv deleted the gdn-changes branch 66 days ago

Login to write a write a comment.

Login via GitHub

Assignees
Labels
Milestone