forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 37
Pull requests: tetherto/qvac-fabric-llm.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Hardened grad-accumulation paths to MoE/hybrid/recurrent models
Apple Metal
ggml
#193
opened Jul 29, 2026 by
zoq
Loading…
Rebase b10069
android
Apple Metal
build
conversion
CUDA
devops
documentation
Improvements or additions to documentation
ggml
model
mtmd
OpenCL
server/ui
server
testing
vendor
Vulkan
#190
opened Jul 24, 2026 by
makaveli10
Loading…
QVAC-22747 infra: add weekly schedule to the CodeScan caller
devops
#189
opened Jul 23, 2026 by
GSServita
Loading…
conversion: register Unlimited-OCR tokenizer hash so it converts end-to-end
conversion
#188
opened Jul 23, 2026 by
olyasir
Loading…
QVAC-20631 TurboVec: fabric vector index (CPU)
android
Apple Metal
build
conversion
CUDA
devops
documentation
Improvements or additions to documentation
examples
ggml
Hexagon
jinja parser
model
mtmd
OpenCL
OpenVINO
server/ui
server
SYCL
testing
vendor
Vulkan
WebGPU
[testing] standalone qwen3vl encoder + CPU repack (do not merge)
documentation
Improvements or additions to documentation
mtmd
perf: ARM CPU conv kernels for DocTR detection (rebased onto temp-9341)
ggml
testing
#162
opened Jun 19, 2026 by
olyasir
Loading…
Enable Android Vulkan int dot builds
android
Apple Metal
build
CUDA
devops
documentation
Improvements or additions to documentation
examples
ggml
python
script
server
testing
Vulkan
#151
opened Jun 14, 2026 by
watsoncsulahack
Loading…
ci: fix Vulkan Docker build failures and GHCR registry timeout
build
devops
#136
opened May 18, 2026 by
Ektisad25
Loading…
cuda: restrict out_prod support to f32 inputs
ggml
Nvidia GPU
#110
opened Mar 19, 2026 by
GuthL
Loading…
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.