-
Notifications
You must be signed in to change notification settings - Fork 16.7k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
vulkan: fix output corruption on GCN 2.0/3.0 (Vulkan 1.2)
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#21787
opened Apr 12, 2026 by
rafikb
Loading…
chat: dedicated DeepSeek v3.2 parser + "official" template
testing
Everything test related
#21785
opened Apr 12, 2026 by
pwilkin
Member
Loading…
tests: skip broken archs in test-llama-archs
testing
Everything test related
#21783
opened Apr 11, 2026 by
stephencox-ict
Loading…
ggml-metal: add Metal kernel for ggml_roll
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
#21782
opened Apr 11, 2026 by
stephencox-ict
Loading…
vendor : update cpp-httplib to 0.42.0
python
python script changes
script
Script related
#21781
opened Apr 11, 2026 by
cabelo
Contributor
Loading…
docs: add guide on how to add multimodal support
documentation
Improvements or additions to documentation
#21778
opened Apr 11, 2026 by
ngxson
Contributor
Loading…
ggml: add graph_reused
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#21764
opened Apr 11, 2026 by
am17an
Contributor
Loading…
CUDA: only init NCCL for setups with multi GPU
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#21761
opened Apr 11, 2026 by
EldarBorge
Loading…
vulkan: Support asymmetric FA in coopmat2 path
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#21753
opened Apr 11, 2026 by
jeffbolznv
Contributor
Loading…
common: honor HTTP_PROXY/HTTPS_PROXY env vars in http client
#21752
opened Apr 11, 2026 by
texasich
Loading…
vulkan: Coalesce Q4_K/Q5_K scale loads in mul_mm
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#21751
opened Apr 10, 2026 by
TheBlueMatt
Contributor
Loading…
server: ensure prompt caching for SWA models
examples
server
#21749
opened Apr 10, 2026 by
shipped-it
Loading…
CUDA: initialize NCCL comms lazily
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#21746
opened Apr 10, 2026 by
JohannesGaessler
Contributor
Loading…
ggml-webgpu: Windows D3D12 fallback for ShaderF16-lacking primary ada…
ggml
changes relating to the ggml tensor library for machine learning
WebGPU
#21744
opened Apr 10, 2026 by
MansfieldPlumbing
Loading…
server: rename python script changes
server
--clear-idle to --cache-idle-slots
examples
python
#21741
opened Apr 10, 2026 by
yychyo
Contributor
Loading…
ggml-webgpu: updated matrix-vector multiplication
ggml
changes relating to the ggml tensor library for machine learning
WebGPU
#21738
opened Apr 10, 2026 by
neha-ha
Contributor
Loading…
Fix gfx1103 performance regression
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#21720
opened Apr 10, 2026 by
matteoserva
Contributor
Loading…
CUDA: Limit DeviceSegmentedSort to immediate mode
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
testing
Everything test related
#21718
opened Apr 10, 2026 by
ORippler
Collaborator
Loading…
TP: fix arbitrary -ot
ggml
changes relating to the ggml tensor library for machine learning
#21717
opened Apr 10, 2026 by
JohannesGaessler
Contributor
Loading…
Previous Next
ProTip!
Add no:assignee to see everything that’s not assigned.