Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
421 Open 5,408 Closed
421 Open 5,408 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

vulkan: matmul gcn tuning ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#13016 opened Apr 18, 2025 by netrunnereve Loading…
CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#13014 opened Apr 18, 2025 by JohannesGaessler Loading…
4
mtmd : merge llava-cli and gemma3-cli into single mtmd-cli examples
#13012 opened Apr 18, 2025 by ngxson • Draft
clip : refactor, add image_manipulation and llava_uhd classes examples
#13011 opened Apr 18, 2025 by ngxson Loading…
Update OneAPI base toolkit to Latest Version for Windows SYCL Backend devops improvements to build systems and github actions SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13007 opened Apr 18, 2025 by kotauchisunsun Loading…
2
Nix portability improvements devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning nix Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
#13005 opened Apr 18, 2025 by hacker1024 Loading…
[SYCL][OPT] Fix reorder optimization for Q4_0 ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13003 opened Apr 18, 2025 by NeoZhangJianyu Loading…
10
make memset range dynamic ggml changes relating to the ggml tensor library for machine learning
#13002 opened Apr 18, 2025 by pockers21 Loading…
3
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling examples ggml changes relating to the ggml tensor library for machine learning
#12995 opened Apr 17, 2025 by max-krasnyansky Loading…
4
[CANN] Add the n_graph_splits performance metric to llama-bench. Ascend NPU issues specific to Ascend NPUs examples
#12994 opened Apr 17, 2025 by bachelor-dou Loading…
@bachelor-dou
9
SYCL: Add non-contiguous support in ROPE ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#12993 opened Apr 17, 2025 by qnixsynapse Loading…
4
Fix convert script for non-hf GLM4 checkpoints python python script changes
#12992 opened Apr 17, 2025 by Tianyue-Zhao Loading…
2 of 4 tasks
sycl: use DNN in the first part of ggml_sycl_mul_mat_batched_sycl ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#12972 opened Apr 16, 2025 by lslusarczyk • Draft
2
Vulkan: Fix Deepseek V2 inference by making ggml_vk_op_supports_incontiguous(GGML_OP_RMS_NORM) return true ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#12960 opened Apr 15, 2025 by stduhpf • Draft
1
5
Resolved half rope,multi-EOS issues in convert_hf_togguf.py for GLM4Z Model python python script changes
#12957 opened Apr 15, 2025 by piDack Loading…
45
rpc : do not wait for response when sending RPC_CMD_SET_TENSOR ggml changes relating to the ggml tensor library for machine learning
#12943 opened Apr 14, 2025 by rgerganov • Draft
4
set b = ub when b > ub with embedding examples server
#12940 opened Apr 14, 2025 by ahmedshakill Loading…
1
llama-bench : Add --override-tensors arg examples
#12922 opened Apr 12, 2025 by 4onen Loading…
15
Get CPU model in ggml_backend_cpu_device_context on FreeBSD ggml changes relating to the ggml tensor library for machine learning
#12902 opened Apr 11, 2025 by yurivict Loading…
4
server : (experimental) vision support via libmtmd examples server
#12898 opened Apr 11, 2025 by ngxson • Draft
6 tasks
11
cuda: fix compilation error (#12893) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#12894 opened Apr 11, 2025 by lizhenneng Loading…
llama-tts : input from stdin examples
#12890 opened Apr 11, 2025 by marcoStocchi Loading…
1
llama-bench: enhance benchmark with improved token throughput measurements examples
#12874 opened Apr 10, 2025 by thevishalagarwal Loading…
20
ggml : add SSE 4.2 and x64 base variant for CPUs without AVX ggml changes relating to the ggml tensor library for machine learning
#12871 opened Apr 10, 2025 by slaren Loading…
1
sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#12858 opened Apr 10, 2025 by Alcpz Loading…
2 of 3 tasks
20
ProTip! Adding no:label will show everything without a label.