Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
396 Open 5,077 Closed
396 Open 5,077 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

(research) experiment with phi-4-multimodal vision support examples python python script changes
#12274 opened Mar 8, 2025 by ngxson • Draft
vulkan: Pad N dimension of B matrix for coopmat2 perf, to avoid bounds checking ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#12273 opened Mar 8, 2025 by jeffbolznv Loading…
vulkan: fix coopmat shader generation when cross-compiling ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#12272 opened Mar 8, 2025 by Icenowy Loading…
2
metal: Cache compiled library at device level Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#12265 opened Mar 8, 2025 by BB-fat • Draft
1
doc: add software architecture and propose PAL in toplevel README.md
#12263 opened Mar 8, 2025 by zhouwg Loading…
Add simple-tts example examples
#12261 opened Mar 8, 2025 by danemadsen Loading…
5
vulkan: optimization proposals for coopmat1 mul_mm ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#12260 opened Mar 7, 2025 by remyoudompheng • Draft
1
vulkan: Adjust coopmat2 tile sizes and selection heuristic ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#12258 opened Mar 7, 2025 by jeffbolznv Loading…
main: add -sysf / --system-prompt-file
#12250 opened Mar 7, 2025 by CISC Loading…
1
5
server : Add verbose output to OAI compatible chat endpoint. android Issues specific to Android Apple Metal https://en.wikipedia.org/wiki/Metal_(API) build Compilation issues devops improvements to build systems and github actions documentation Improvements or additions to documentation examples ggml changes relating to the ggml tensor library for machine learning Kompute https://github.com/KomputeProject/kompute/ nix Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment Nvidia GPU Issues specific to Nvidia GPUs python python script changes script Script related server SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related Vulkan Issues specific to the Vulkan backend
#12246 opened Mar 7, 2025 by mglambda Loading…
3
clang-tidy : disable bugprone-branch-clone
#12244 opened Mar 7, 2025 by ggerganov Loading…
1
Fix rocWMMA build documentation documentation Improvements or additions to documentation
#12243 opened Mar 7, 2025 by Headcrabed Loading…
Issues while enabling MMA support on AIX machines ggml changes relating to the ggml tensor library for machine learning
#12241 opened Mar 7, 2025 by mehendarkarprajwal Loading…
1
2
tests: use adaptive number of threads testing Everything test related
#12236 opened Mar 6, 2025 by JohannesGaessler Loading…
2
Optimized DeepSeek V2/V3 implementation (MLA + flash attention) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#12227 opened Mar 6, 2025 by jukofyork • Draft
16
opencl: use OpenCL C standard supported by the device ggml changes relating to the ggml tensor library for machine learning
#12221 opened Mar 6, 2025 by linehill Loading…
[DRAFT]build: build llama.cpp with cygwin on Windows
#12215 opened Mar 6, 2025 by zhouwg • Draft
feat(CMakeLists): Add MSVC-specific compiler warning flags in CMake configuration ggml changes relating to the ggml tensor library for machine learning
#12206 opened Mar 5, 2025 by 25077667 Loading…
1
SYCL: Rename oneMKL to oneMath documentation Improvements or additions to documentation examples ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#12192 opened Mar 5, 2025 by Rbiessy Loading…
23
libfuse3 supported mounting split gguf's to a single in-memory file examples
#12189 opened Mar 5, 2025 by matbee-eth • Draft
vulkan: double buffer scale caches ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#12188 opened Mar 4, 2025 by netrunnereve Loading…
4
fix: AVX2 intrinsics, const correctness, and SIMD headers build Compilation issues ggml changes relating to the ggml tensor library for machine learning
#12186 opened Mar 4, 2025 by sandboxyer Loading…
CUDA: Improve flash decoding kernel GPU occupancy for BS=1 case ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#12183 opened Mar 4, 2025 by gaugarg-nv Loading…
1 of 3 tasks
13
llama : refactor llama_context, llama_kv_cache, llm_build_context (v2) android Issues specific to Android examples python python script changes server
#12181 opened Mar 4, 2025 by ggerganov Loading…
CUDA/HIP: refractor mmqv to unify the calculation of nwarps and rows per block between host and device code. ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#12177 opened Mar 4, 2025 by IMbackK Loading…
11
ProTip! Mix and match filters to narrow down what you’re looking for.