-
Notifications
You must be signed in to change notification settings - Fork 12.5k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fix kq_scale for the attention layers of PLaMo2
python
python script changes
#14892
opened Jul 26, 2025 by
mitmul
Loading…
SYCL: Add set_rows support for quantized types
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#14883
opened Jul 26, 2025 by
qnixsynapse
Loading…
GGML: Fix leak of backend buffer memory address in RPC
ggml
changes relating to the ggml tensor library for machine learning
#14882
opened Jul 26, 2025 by
struct
Loading…
model: add hunyuan dense
python
python script changes
#14878
opened Jul 25, 2025 by
stevenkuang-tencent
Loading…
sync : ggml
ggml
changes relating to the ggml tensor library for machine learning
script
Script related
#14873
opened Jul 25, 2025 by
ggerganov
Loading…
Extend test case filtering
testing
Everything test related
#14865
opened Jul 24, 2025 by
tlemo
Loading…
Adding chat template support for Granite model
testing
Everything test related
#14864
opened Jul 24, 2025 by
smdesai
Loading…
mtmd : add support for Voxtral
examples
python
python script changes
#14862
opened Jul 24, 2025 by
ngxson
Loading…
vulkan: skip empty set_rows to avoid invalid API usage
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#14860
opened Jul 24, 2025 by
jeffbolznv
Loading…
test-backend-ops: enables perf/eval testing of composite ops
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
#14833
opened Jul 23, 2025 by
etasnadi
Loading…
graph : reduce splits for recurrent and hybrid models
performance
Speed related topics
#14825
opened Jul 23, 2025 by
compilade
Loading…
sycl: refactor quantization to q8_1
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#14815
opened Jul 22, 2025 by
Alcpz
Loading…
feat(batched): Add functionality to upload benchmark test results
examples
#14811
opened Jul 22, 2025 by
MengAiDev
Loading…
convert : handle pre-quantized models
enhancement
New feature or request
python
python script changes
#14810
opened Jul 22, 2025 by
compilade
Loading…
2 tasks
opencl: tiled mul_mat with local memory for f16 and f32
ggml
changes relating to the ggml tensor library for machine learning
OpenCL
Issues specific to the OpenCL backend
Add LLaDA 8b Diffusion model
examples
python
python script changes
#14771
opened Jul 19, 2025 by
am17an
Loading…
docs : mention apt installation method
documentation
Improvements or additions to documentation
#14766
opened Jul 19, 2025 by
vp2177
Loading…
feat: Add extended sampling API with candidate token lists #14612
#14765
opened Jul 19, 2025 by
baonudesifeizhai
Loading…
webui: add missing messages in export (#13552)
examples
server
#14764
opened Jul 18, 2025 by
srogmann
Loading…
Fix MinicpmV model converter and clip to avoid using hardcode.
examples
python
python script changes
#14750
opened Jul 18, 2025 by
gryffindor-rr
Loading…
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.