forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 2
Pull requests: edwinbrowwn/llama.cpp-rdna2
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
qwen4exp: port selected upstream performance paths
model
testing
#44
opened Sep 7, 2026 by
edwinbrowwn
Owner
Loading…
KVarN gfx1030: integrate PR #38 with current master and sidecars
Apple Metal
Ascend NPU
build
conversion
CUDA
devops
documentation
Improvements or additions to documentation
ggml
model
OpenCL
server
SYCL
testing
Vulkan
#41
opened Sep 4, 2026 by
edwinbrowwn
Owner
Loading…
KVarN gfx1030: runtime-cc decode_vector fix + merge API reconciliation
Apple Metal
Ascend NPU
build
conversion
CUDA
devops
documentation
Improvements or additions to documentation
ggml
model
OpenCL
server
SYCL
testing
Vulkan
#38
opened Sep 3, 2026 by
ikantkode
Loading…
ggml-cuda: tune RDNA head-size-256 FA occupancy
CUDA
ggml
testing
#26
opened Aug 23, 2026 by
edwinbrowwn
Owner
•
Draft
dsv4 split mode tensor
AMD ZenDNN
conversion
CUDA
devops
documentation
Improvements or additions to documentation
examples
ggml
model
mtmd
server
SYCL
testing
Vulkan
WebGPU
#6
opened Aug 1, 2026 by
edwinbrowwn
Owner
Loading…
ProTip!
Filter pull requests by the default branch with base:master.