-
Notifications
You must be signed in to change notification settings - Fork 13.8k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
vulkan: more FA details in vk_perf_logger
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#17443
opened Nov 23, 2025 by
jeffbolznv
Loading…
We want newer packages for Vulkan
devops
improvements to build systems and github actions
#17439
opened Nov 22, 2025 by
ericcurtin
Loading…
HIP: enable mul_mat_f for RDNA4
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#17437
opened Nov 22, 2025 by
zhang-hui-yulo
Loading…
docs: vulkan add GGML_VK_ALLOW_SYSMEM_FALLBACK=1 docs
documentation
Improvements or additions to documentation
#17436
opened Nov 22, 2025 by
taronaeo
Loading…
CANN: Define issues specific to Ascend NPUs
ggml
changes relating to the ggml tensor library for machine learning
cann_graph_update_required before macro
Ascend NPU
#17434
opened Nov 21, 2025 by
rauletorresc
Loading…
Fix convert_hf_to_gguf.py script on s390x
python
python script changes
#17431
opened Nov 21, 2025 by
AlekseiNikiforovIBM
Loading…
[Hybrid] Create checkpoints while processing the prompt
examples
server
#17428
opened Nov 21, 2025 by
whoreson
Loading…
common : throttle download progress output to reduce IO flush
#17427
opened Nov 21, 2025 by
angt
Loading…
cmake : simplify build info detection using standard variables
build
Compilation issues
#17423
opened Nov 21, 2025 by
angt
Loading…
vulkan: Implement top-k
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#17418
opened Nov 21, 2025 by
jeffbolznv
•
Draft
Vulkan: Add changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
GGML_OP_GET_REL_POS
ggml
#17417
opened Nov 20, 2025 by
AgainstEntropy
Loading…
llama.android : Rewrite Android binding (w/o cpu_features dep)
android
Issues specific to Android
documentation
Improvements or additions to documentation
examples
ggml
changes relating to the ggml tensor library for machine learning
#17413
opened Nov 20, 2025 by
naco-siren
Loading…
CANN: supports out_prod operator for F32 and F16
Ascend NPU
issues specific to Ascend NPUs
ggml
changes relating to the ggml tensor library for machine learning
#17406
opened Nov 20, 2025 by
TianHao324
Loading…
CANN: Add MROPE and IMROPE support
Ascend NPU
issues specific to Ascend NPUs
ggml
changes relating to the ggml tensor library for machine learning
#17401
opened Nov 20, 2025 by
hipudding
Loading…
models : add Nougat OCR support with mBART and Swin Transformer
examples
model
Model specific
python
python script changes
#17398
opened Nov 20, 2025 by
h9-tec
Loading…
6 of 10 tasks
ggml-hexagon: Initial Hexagon v68/v69 support
ggml
changes relating to the ggml tensor library for machine learning
#17394
opened Nov 20, 2025 by
mediouni-m
Loading…
fix: /metrics endpoint returning JSON-escaped Prometheus format
examples
server
#17386
opened Nov 19, 2025 by
o7si
Loading…
ggml : enhance rel-pos and window ops with CUDA support
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
testing
Everything test related
#17383
opened Nov 19, 2025 by
bluebread
Loading…
llama : update worst-case graph for unified cache
devops
improvements to build systems and github actions
examples
#17379
opened Nov 19, 2025 by
ggerganov
Loading…
Previous Next
ProTip!
Adding no:label will show everything without a label.