-
Notifications
You must be signed in to change notification settings - Fork 12.2k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
kv-cells : fix tracking of seq_pos during cache reuse
#14339
opened Jun 23, 2025 by
ggerganov
Loading…
Fixes for rwkv-world template and the missing inputs.use_jinja in llama-cli
examples
#14336
opened Jun 23, 2025 by
MollySophia
Loading…
vulkan: update windows SDK in CI
devops
improvements to build systems and github actions
#14334
opened Jun 22, 2025 by
jeffbolznv
Loading…
vulkan: lock accesses of pinned_memory vector
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#14333
opened Jun 22, 2025 by
jeffbolznv
Loading…
ggml-cpu: Pass on tag_name to the feature scoring
ggml
changes relating to the ggml tensor library for machine learning
#14332
opened Jun 22, 2025 by
ckastner
Loading…
CUDA/HIP: optimize mmv paths taken for HIP/CDNA
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#14324
opened Jun 22, 2025 by
IMbackK
Loading…
Fix appearance of the chats list context menu for the browser Safari
examples
server
#14322
opened Jun 22, 2025 by
rntk
Loading…
ggml-cpu: enable IBM NNPA Vector Intrinsics
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
#14317
opened Jun 21, 2025 by
taronaeo
Loading…
GitHub workflow: set RPATH to "@loader_path" / "$ORIGIN" to ensure executables and dynamic libraries search for dependencies in their origin directory.
devops
improvements to build systems and github actions
#14309
opened Jun 20, 2025 by
rotemdan
Loading…
Fix Windows Null Pointer Bug and Enhance Memory Operations in ggml-sycl
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#14290
opened Jun 20, 2025 by
MengAiDev
Loading…
kv-cache : use ggml_set_rows
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
examples
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
#14285
opened Jun 19, 2025 by
ggerganov
Loading…
4 tasks
CUDA: mul_mat_v support for batch sizes > 1
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#14262
opened Jun 18, 2025 by
JohannesGaessler
Loading…
opencl: ref count changes relating to the ggml tensor library for machine learning
ggml_backend_opencl_context
and refactor profiling
ggml
#14254
opened Jun 18, 2025 by
lhez
Loading…
Add SmolLM3
documentation
Improvements or additions to documentation
python
python script changes
#14240
opened Jun 17, 2025 by
Vaibhavs10
•
Draft
MODEL: Falcon-H1 support
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
python
python script changes
testing
Everything test related
#14238
opened Jun 17, 2025 by
younesbelkada
•
Draft
Mtmd: add a way to select device for vision encoder
examples
#14236
opened Jun 17, 2025 by
stduhpf
Loading…
ggml: introduce GGML_NUMA_MIGRATE to optimize cross NUMA op computation
examples
ggml
changes relating to the ggml tensor library for machine learning
#14232
opened Jun 17, 2025 by
wenlujon
Loading…
logit_bias: apply configurable escalating EOG bias at low n_remain
examples
server
testing
Everything test related
#14229
opened Jun 16, 2025 by
graehl
Loading…
tests : enhance llama-bench with separate timings (pp/gen t/s), added n_threads_batch
examples
#14219
opened Jun 16, 2025 by
thad0ctor
Loading…
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.