Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
376 Open 4,921 Closed
376 Open 4,921 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

ci : fix (again) arm64 build fails devops improvements to build systems and github actions
#11895 opened Feb 15, 2025 by ngxson Loading…
CUDA: use async data loading for FlashAttention ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#11894 opened Feb 15, 2025 by JohannesGaessler Loading…
vulkan: Added GGML_VK_DEVICE{idx}_MEMORY environment variable for setting device memory to manually allocate workload. ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#11878 opened Feb 14, 2025 by System233 Loading…
llama : private llama_batch examples server
#11875 opened Feb 14, 2025 by ngxson Loading…
1
2
Overlap CUDA graph building and processing to minimize GPU idle time and improve tokens per seconds performance. ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#11867 opened Feb 14, 2025 by aendk Loading…
1
server : add condition for grammar examples server
#11863 opened Feb 14, 2025 by danbev Loading…
1
Upgrade init_tensor API to return a ggml_status ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related Vulkan Issues specific to the Vulkan backend
#11854 opened Feb 14, 2025 by WilliamTambellini Loading…
1
WebUI - Mcp SSE server support in client examples python python script changes server
#11853 opened Feb 14, 2025 by brucepro Loading…
vocab : add special infill tokens for CodeLlama
#11850 opened Feb 13, 2025 by danbev Loading…
MUSA: enable dp4a and fix compile errors on ARM64 build Compilation issues documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#11843 opened Feb 13, 2025 by BodhiHu Loading…
17
vulkan: improve im2col and RDNA1 performance ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#11826 opened Feb 12, 2025 by daniandtheweb Loading…
13
cmake: Fix ggml backend dependencies and installation ggml changes relating to the ggml tensor library for machine learning
#11818 opened Feb 12, 2025 by vvuksanovic Loading…
Improved KV cache loading performance for Vulkan, resulting in a 20x …
#11815 opened Feb 12, 2025 by idales Loading…
1
llama-mmap: use MAP_PRIVATE instead of MAP_SHARED
#11798 opened Feb 10, 2025 by iehgit Loading…
1
Add Granite Vision Support examples ggml changes relating to the ggml tensor library for machine learning python python script changes
#11794 opened Feb 10, 2025 by alex-jw-brooks Loading…
15
ggml: move kvalues_iq4nl definition to ggml-common.h ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#11785 opened Feb 10, 2025 by HungMingWu Loading…
chore: update ggml-cpu-aarch64.cpp ggml changes relating to the ggml tensor library for machine learning
#11782 opened Feb 10, 2025 by eltociear Loading…
server (webui): Fix issue with muliple <think> tags in response examples server
#11779 opened Feb 10, 2025 by stduhpf Loading…
8
ggml : fix more imatrix nan cases ggml changes relating to the ggml tensor library for machine learning
#11773 opened Feb 9, 2025 by slaren Loading…
1
5
vulkan: implement several ops relevant for ggml_opt ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#11769 opened Feb 9, 2025 by remyoudompheng Loading…
13
ci: fix certificate revocation error failures on windows workers (WIP) devops improvements to build systems and github actions
#11761 opened Feb 8, 2025 by ochafik • Draft
ggml-cpu-aarch64: Fix compilation issues ggml changes relating to the ggml tensor library for machine learning
#11745 opened Feb 8, 2025 by MarsDoge Loading…
blas build: use configuration from pkg_check_modules(DepBLAS openblas) and alike ggml changes relating to the ggml tensor library for machine learning
#11741 opened Feb 7, 2025 by khumarahn • Draft
4
ggml : replace reallocation to reuse vector ggml changes relating to the ggml tensor library for machine learning
#11722 opened Feb 6, 2025 by lexasub • Draft
2
Use named LOG_COL_* colors in examples examples
#11694 opened Feb 6, 2025 by xndcn Loading…
ProTip! Updated in the last three days: updated:>2025-02-12.