Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
509 Open 6,756 Closed
509 Open 6,756 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

vulkan: Allow fallback to sysmem memory when vidmem is full ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15649 opened Aug 28, 2025 by jeffbolznv Loading…
gguf-py: reduce peak RAM during convert by streaming dtype casts python python script changes
#15648 opened Aug 28, 2025 by igloo58 Loading…
1
[SERVER] Added documentation for parallel_tool_calls param documentation Improvements or additions to documentation examples server
#15647 opened Aug 28, 2025 by ExtReMLapin Loading…
1
tools: update llama-bench to include TTFT, E2E, ITL metrics examples
#15643 opened Aug 28, 2025 by taronaeo Loading…
Catch up to the upstream Apple Metal https://en.wikipedia.org/wiki/Metal_(API) Ascend NPU issues specific to Ascend NPUs documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs OpenCL Issues specific to the OpenCL backend python python script changes script Script related SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related Vulkan Issues specific to the Vulkan backend
#15642 opened Aug 28, 2025 by skyne98 Loading…
granite embedding small support (ModernBert arch) python python script changes
#15641 opened Aug 28, 2025 by ryan-mangeno • Draft
6
Hermes 2 tool calling : fixed crash when <tool_call> had a newline before it
#15639 opened Aug 28, 2025 by ExtReMLapin Loading…
1
1
batch : add pad_equal [RFC]
#15636 opened Aug 28, 2025 by ggerganov • Draft
Refactor server.cpp: Split monolithic file into modular components examples server
#15632 opened Aug 28, 2025 by Copilot AI • Draft
@ericcurtin @Copilot
1
CUDA: fuse adds, fuse add with rms norm ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#15631 opened Aug 28, 2025 by am17an Loading…
16
server : enable /slots by default and make it secure examples python python script changes server
#15630 opened Aug 28, 2025 by ggerganov Loading…
CANN: fix RoPE cache issue on multi-device Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#15629 opened Aug 28, 2025 by hipudding Loading…
@hipudding
4
Possible fix: use ne0..ne3 (dst dims) instead of ne00..ne03 in ggml_compute_forward_dup_f16 ggml changes relating to the ggml tensor library for machine learning
#15626 opened Aug 28, 2025 by kperreau Loading…
1
ggml : add ggml_mul_mat_id_set_prec and use in llama.cpp ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15619 opened Aug 27, 2025 by ggerganov Loading…
1
7
kleidiai: fix GGML_ASSERT(*cur_backend_id != -1) failed ggml changes relating to the ggml tensor library for machine learning
#15614 opened Aug 27, 2025 by chaxu01 Loading…
2
musa: fix build warnings ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#15611 opened Aug 27, 2025 by yeahdongcn • Draft
Partial code documentation documentation Improvements or additions to documentation
#15601 opened Aug 26, 2025 by grig95 Loading…
fix(ggml-sycl): add synchronization before exiting argsort kernel ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#15582 opened Aug 26, 2025 by MengAiDev Loading…
1
5
Model: Seed OSS thinking + tool call support testing Everything test related
#15552 opened Aug 24, 2025 by pwilkin Loading…
2
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest MSE error examples
#15550 opened Aug 24, 2025 by EAddario • Draft
2
vulkan: mul_mat_id coopmat2 optimizations ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15546 opened Aug 24, 2025 by jeffbolznv Loading…
vulkan: use memory budget extension to read memory usage ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15545 opened Aug 24, 2025 by giladgd Loading…
3
vulkan: Skip syncing for prealloc_y when it is reused ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#15544 opened Aug 24, 2025 by jeffbolznv Loading…
model : add grok-2 support model Model specific python python script changes
#15539 opened Aug 24, 2025 by CISC • Draft
1
33
Deepseek V3.1 thinking mode is the default examples server testing Everything test related
#15533 opened Aug 23, 2025 by createthis Loading…
7
ProTip! Type g i on any issue or pull request to go back to the issue listing page.