-
Notifications
You must be signed in to change notification settings - Fork 14.1k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
server: add encoder-decoder model support (T5, BART, MADLAD)
examples
server
#17956
opened Dec 12, 2025 by
Turee
Loading…
ci: Change the openEuler-cann version and the container pull method
devops
improvements to build systems and github actions
#17953
opened Dec 12, 2025 by
xuedinge233
Loading…
ggml-cpu:fix RISC-V Q4_0 repack select and RVV feature reporting
ggml
changes relating to the ggml tensor library for machine learning
#17951
opened Dec 12, 2025 by
ixgbe
Loading…
scripts: add script to compare logprobs of llama.cpp against other frameworks
python
python script changes
script
Script related
#17947
opened Dec 11, 2025 by
ngxson
Loading…
mtmd: explicitly forbidden inclusion of private header and libcommon
examples
#17946
opened Dec 11, 2025 by
ngxson
Loading…
models : fix the attn_factor for mistral3 graphs + improve consistency
model
Model specific
python
python script changes
#17945
opened Dec 11, 2025 by
ggerganov
Loading…
vulkan: Add perf logger mode with concurrency
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#17944
opened Dec 11, 2025 by
jeffbolznv
Loading…
vulkan: support get_rows for i32
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#17941
opened Dec 11, 2025 by
jeffbolznv
Loading…
CUDA: fix overflow in MMA kernel without stream-k
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#17939
opened Dec 11, 2025 by
JohannesGaessler
Loading…
CANN: CONV_TRANSPOSE_1D operator: supporting the cases where (op->src[0]->ne[0] - 1) > 255
Ascend NPU
issues specific to Ascend NPUs
ggml
changes relating to the ggml tensor library for machine learning
#17934
opened Dec 11, 2025 by
Intellouis
Loading…
Webui: Disable attachment button and model selector button when prompt textbox is disabled.
examples
server
#17925
opened Dec 11, 2025 by
dariusjlukas
Loading…
Gigachat 3 tool parser and tests
testing
Everything test related
#17924
opened Dec 11, 2025 by
Mishusha
Loading…
ggml-hexagon: gelu operation
ggml
changes relating to the ggml tensor library for machine learning
#17921
opened Dec 10, 2025 by
joeldushouyu
•
Draft
Restore clip's cb() to its rightful glory - extract common debugging elements in llama
examples
#17914
opened Dec 10, 2025 by
pwilkin
Loading…
Make
LlamaData utility functions static in llama-run
examples
#17913
opened Dec 10, 2025 by
rauletorresc
Loading…
server: fix crash when batch > ubatch with embeddings (#12836)
examples
server
#17912
opened Dec 10, 2025 by
yifant-code
Loading…
CUDA: experimental native mxfp4 support for blackwell [WIP]
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
model: add glm-asr support
examples
python
python script changes
#17901
opened Dec 10, 2025 by
piDack
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2025-11-12.