-
Notifications
You must be signed in to change notification settings - Fork 12.7k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
ggml: riscv: add riscv spacemit backend
build
Compilation issues
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
#15288
opened Aug 13, 2025 by
alex-spacemit
Loading…
Add comprehensive Copilot instructions with Python environment, server testing, and backend hardware notes
devops
improvements to build systems and github actions
HIP: Cleanup hipification header
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
vulkan.Dockerfile: install vulkan SDK using tarball
devops
improvements to build systems and github actions
#15282
opened Aug 13, 2025 by
yeahdongcn
Loading…
vulkan: optimize rms_norm, and allow the work to spread across multiple SMs
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#15281
opened Aug 13, 2025 by
jeffbolznv
•
Draft
arm64: add i8mm route with SVE ggml_vec_dot_q4_K_q8_K and ggml_vec_dot_q6_K_…
ggml
changes relating to the ggml tensor library for machine learning
#15277
opened Aug 13, 2025 by
fj-y-saito
Loading…
Q6_K - Block Interleaving Implementation for x86 SIMD (AVX512/AVX2)
ggml
changes relating to the ggml tensor library for machine learning
#15275
opened Aug 12, 2025 by
Srihari-mcw
Loading…
opencl: add initial mxfp4 support via mv
ggml
changes relating to the ggml tensor library for machine learning
OpenCL
Issues specific to the OpenCL backend
#15270
opened Aug 12, 2025 by
lhez
Loading…
ci: Enable GGML_CPU_ALL_VARIANTS for ARM
devops
improvements to build systems and github actions
#15267
opened Aug 12, 2025 by
ckastner
Loading…
Apple NPU acceleration integrated into llama.cpp, using MiniCPM-V 4.0 as an example.
examples
python
python script changes
#15262
opened Aug 12, 2025 by
tc-mb
Loading…
WIP: ggml-cuda: Add bf16 cuda support to fattn (Flash Attention)
examples
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
python
python script changes
#15261
opened Aug 12, 2025 by
eous
Loading…
musa: fix build warnings
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#15258
opened Aug 12, 2025 by
yeahdongcn
Loading…
vulkan: fuse adds
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#15252
opened Aug 11, 2025 by
jeffbolznv
Loading…
ci : Enable pre-built cuda releases on ubuntu (#5106)
devops
improvements to build systems and github actions
#15249
opened Aug 11, 2025 by
michaelgiba
Loading…
Fixes #15247 | Update chat.cpp to support (at least) qwen3 reasoning + tool_choice = required
#15248
opened Aug 11, 2025 by
ExtReMLapin
Loading…
vulkan: perf_logger improvements
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#15246
opened Aug 11, 2025 by
jeffbolznv
Loading…
ci : Fix -Werror=return-type in clip.cpp so ci/run.sh can run without issue
examples
#15221
opened Aug 11, 2025 by
michaelgiba
Loading…
Adding Resume for curl downloads
testing
Everything test related
#15217
opened Aug 10, 2025 by
taf2
Loading…
introduce how to build with Vulkan on Raspbian OS
documentation
Improvements or additions to documentation
#15206
opened Aug 10, 2025 by
MaoJianwei
Loading…
webui: prettify styling
examples
server
#15201
opened Aug 9, 2025 by
olegshulyakov
Loading…
11 tasks done
server: implementation of v1/completions echo logprobs support
examples
server
#15189
opened Aug 9, 2025 by
fo40225
Loading…
ggml: add changes relating to the ggml tensor library for machine learning
testing
Everything test related
conv3d
op
ggml
#15182
opened Aug 8, 2025 by
rmatif
Loading…
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.