Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
643 Open 8,415 Closed
643 Open 8,415 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

ggml-cuda: refactor cuda graph usage ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#18637 opened Jan 6, 2026 by am17an Loading…
alloc : skip unassigned leafs ggml changes relating to the ggml tensor library for machine learning
#18636 opened Jan 6, 2026 by ggerganov • Draft
1
Added note for compiling on integrated GPUs documentation Improvements or additions to documentation
#18633 opened Jan 6, 2026 by alosslessdev • Draft
vulkan: optimize ssm_scan ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18630 opened Jan 5, 2026 by jeffbolznv Loading…
ggml-webgpu: Fix GGML_MEM_ALIGN to 8 for emscripten. ggml changes relating to the ggml tensor library for machine learning
#18628 opened Jan 5, 2026 by yomaytk Loading…
1
rpc : implement event and async backend APIs ggml changes relating to the ggml tensor library for machine learning
#18626 opened Jan 5, 2026 by rgerganov • Draft
2
CANN: Remove unused functions Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#18625 opened Jan 5, 2026 by rauletorresc Loading…
CANN: Rename get_env to get_env_as_lowercase Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#18624 opened Jan 5, 2026 by rauletorresc Loading…
sampling: add tail-free (TFS) sampling
#18612 opened Jan 5, 2026 by viralvgupta Loading…
Hexagon add support for f16/f32 flash attention, scale, set-rows and improve f16/32 matmul ggml changes relating to the ggml tensor library for machine learning
#18611 opened Jan 5, 2026 by max-krasnyansky Loading…
3
ggml webgpu: initial flashattention implementation ggml changes relating to the ggml tensor library for machine learning
#18610 opened Jan 5, 2026 by reeselevine Loading…
4
Fix grammar parsing issues to prevent stack overflow and hangs testing Everything test related
#18604 opened Jan 5, 2026 by aagit Loading…
common: build as shared library when BUILD_SHARED_LIBS is ON
#18602 opened Jan 5, 2026 by rsauciuc Loading…
memory : add llama_memory_hybrid_iswa
#18601 opened Jan 4, 2026 by tdakhran Loading…
server: add group support for router mode model presets examples server
#18600 opened Jan 4, 2026 by ssam18 Loading…
1
1
ggml: fix assertion in ggml_build_backward_expand for inplace operations ggml changes relating to the ggml tensor library for machine learning
#18589 opened Jan 4, 2026 by nlasky2000-dot Loading…
1
mtmd : fix integer overflow when n_tokens equals INT32_MIN examples
#18588 opened Jan 4, 2026 by ylwango613 Loading…
8
ggml-backend: allow free = 0 and total = 0 to use host memory info ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#18587 opened Jan 4, 2026 by taronaeo Loading…
1
2
Fix division by zero vulnerability in gguf_init_from_file_impl ggml changes relating to the ggml tensor library for machine learning
#18586 opened Jan 4, 2026 by ylwango613 Loading…
11
gguf-hash: add RVV tensor hashing using xxh3 examples
#18576 opened Jan 4, 2026 by ixgbe Loading…
4
GGML RPC - Add support for Unix Domain Sockets examples ggml changes relating to the ggml tensor library for machine learning
#18574 opened Jan 3, 2026 by struct • Draft
2
add option --tensor-type-file to llama-quantize examples
#18572 opened Jan 3, 2026 by EugeoSynthesisThirtyTwo Loading…
1
llama: max ctx by default, fix fit magic number examples testing Everything test related
#18567 opened Jan 3, 2026 by JohannesGaessler Loading…
1
2
cuda : check src shapes for CUDA graphs ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#18561 opened Jan 3, 2026 by ggerganov • Draft
9
llama-bench: Add --no-fail (-nf) option examples
#18554 opened Jan 2, 2026 by SamAcctX Loading…
ProTip! Add no:assignee to see everything that’s not assigned.