Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
494 Open 6,510 Closed
494 Open 6,510 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

opencl: support sinks in soft_max (attn sinks) ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#15152 opened Aug 7, 2025 by lhez Loading…
sycl: Fix and disable more configurations of mul_mat ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#15151 opened Aug 7, 2025 by Rbiessy Loading…
3
kleidiai: fix unsigned overflow bug ggml changes relating to the ggml tensor library for machine learning
#15150 opened Aug 7, 2025 by chaxu01 Loading…
3
chat : Avoid partial reasoning tags in response content testing Everything test related
#15149 opened Aug 7, 2025 by p1-0tr Loading…
SVE support for exponential functions ggml changes relating to the ggml tensor library for machine learning
#15145 opened Aug 7, 2025 by s-goto-11 Loading…
OpenCL: allow mixed f16/f32 add ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#15140 opened Aug 6, 2025 by rmatif Loading…
CUDA: Optimize reduce_rows_f32 kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#15132 opened Aug 6, 2025 by ORippler Loading…
14
vulkan: support flash attention sinks ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15126 opened Aug 6, 2025 by jeffbolznv Loading…
Add T5Gemma support #14940 python python script changes
#15123 opened Aug 6, 2025 by baonudesifeizhai Loading…
4
ggml: aarch64: Implement SVE F16 kernels for vector functions ggml changes relating to the ggml tensor library for machine learning
#15115 opened Aug 6, 2025 by Vithulep Loading…
1
gguf-py : add Numpy MXFP4 de/quantization support ggml changes relating to the ggml tensor library for machine learning python python script changes Tensor Encoding Scheme https://github.com/ggerganov/llama.cpp/wiki/Tensor-Encoding-Schemes
#15111 opened Aug 6, 2025 by compilade Loading…
5
vulkan: Add env var to disable host visible vidmem ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15109 opened Aug 6, 2025 by jeffbolznv Loading…
mtmd: server: Support basic multimodal data in /completions endpoint of server examples server
#15108 opened Aug 6, 2025 by 65a Loading…
8
CUDA/HIP: ssm-scan: switch from shared memory to reisters, fixes indexing problem on warp64 devices ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#15101 opened Aug 5, 2025 by IMbackK Loading…
4
model : add reasoning/tool parsing to Llama 3.x Nemotron testing Everything test related
#15083 opened Aug 5, 2025 by aldehir Loading…
CANN: GGML_OP_CPY optimization Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#15070 opened Aug 4, 2025 by noemotiovon Loading…
1
quantize : configurable neutral imatrix prior examples generation quality Quality of model output need feedback Testing and feedback with results are needed research 🔬
#15060 opened Aug 3, 2025 by compilade • Draft
1 of 3 tasks
11
ggml-cpu : add basic RVV support for vector f32 ops ggml changes relating to the ggml tensor library for machine learning
#15057 opened Aug 3, 2025 by xctan Loading…
vulkan: conv2d addressing optimizations ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15056 opened Aug 3, 2025 by jeffbolznv Loading…
16
Support streaming delta.reasoning_content in WebUI examples server
#15052 opened Aug 3, 2025 by mostlygeek Loading…
1
Fix: respect localStorage base URL override in Web UI examples server
#15048 opened Aug 3, 2025 by insanerest Loading…
Fix: flush partial stop string when <EOG> is reached in /completion endpoint in streaming mode examples server
#15007 opened Aug 1, 2025 by matteoserva Loading…
fix compile bug when the BASE_CUDA_DEV_CONTAINER is based on Ubuntu 2… devops improvements to build systems and github actions
#15005 opened Aug 1, 2025 by simevo Loading…
1
Add support for CogVLM model examples python python script changes
#15002 opened Aug 1, 2025 by Tianyue-Zhao Loading…
2 of 4 tasks
9
OpenCL: add initial FA support ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#14987 opened Jul 31, 2025 by rmatif Loading…
3
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.