forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 40
Pull requests: tetherto/qvac-fabric-llm.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
QVAC-24627 infra: cancel superseded CI runs on push and dispatch
devops
#235
opened Sep 4, 2026 by
tobi-legan
Loading…
ggml: overlap dense FFN weight transfers with prompt processing
AMD ZenDNN
Apple Metal
Ascend NPU
CUDA
examples
ggml
Hexagon
IBM zDNN
OpenCL
OpenVINO
SYCL
Vulkan
WebGPU
#233
opened Sep 4, 2026 by
amangupta-tether
Loading…
xdna : add AMD XDNA backend with first NPU GEMM kernel
documentation
Improvements or additions to documentation
ggml
#224
opened Aug 28, 2026 by
maximbibik-itrex
•
Draft
xdna : selective hybrid CPU/NPU execution for Qwen3.5
documentation
Improvements or additions to documentation
ggml
testing
#223
opened Aug 28, 2026 by
maximbibik-itrex
•
Draft
Rebase b10549
android
Apple Metal
build
conversion
CUDA
devops
documentation
Improvements or additions to documentation
ggml
model
mtmd
OpenCL
server/ui
server
testing
vendor
Vulkan
WebGPU
#217
opened Aug 27, 2026 by
gagallo7
Loading…
QVAC-24124: set tensor 2d hash
devops
ggml
testing
#215
opened Aug 25, 2026 by
amangupta-tether
Loading…
fix: surface a failed K-shift instead of decoding over stale K
server
#213
opened Aug 25, 2026 by
yingying0906
•
Draft
ci: fix Vulkan Docker build failures and GHCR registry timeout
build
devops
#136
opened May 18, 2026 by
Ektisad25
Loading…
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.