Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
462 Open 6,018 Closed
462 Open 6,018 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

logit_bias: apply configurable escalating EOG bias at low n_remain examples server testing Everything test related
#14229 opened Jun 16, 2025 by graehl Loading…
cmake: remove shader-gen step-targets from ggml-vulkan ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#14226 opened Jun 16, 2025 by bandoti Loading…
1
2
ggml-cpu : remove the weak alias trick ggml changes relating to the ggml tensor library for machine learning
#14221 opened Jun 16, 2025 by xctan Loading…
1
tests : enhance llama-bench with separate timings (pp/gen t/s), added n_threads_batch examples
#14219 opened Jun 16, 2025 by thad0ctor Loading…
3
ubatch : new splitting logic
#14217 opened Jun 16, 2025 by ggerganov • Draft
sycl: Cleanup codepaths in Get Rows in sycl backend ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#14215 opened Jun 16, 2025 by ShanoToni Loading…
2
llama: fix compilation warning (#464)
#14209 opened Jun 16, 2025 by L33TSP34KER Loading…
5
gguf-py: Make sentencepiece optional python python script changes
#14200 opened Jun 15, 2025 by Ahajha Loading…
2
webui: save model name with conversation history (#13570) examples server
#14192 opened Jun 15, 2025 by deepanshu2015 Loading…
2
ci: re-enable rocm linux build, reduce the built targets to the ones currently available in rocblas devops improvements to build systems and github actions
#14184 opened Jun 14, 2025 by IMbackK Loading…
ggml : implement GLU for split up/gate 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
#14181 opened Jun 14, 2025 by CISC Loading…
11
ggml : implement REGLU/GEGLU/SWIGLU ops Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning help wanted Extra attention is needed 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
#14158 opened Jun 12, 2025 by CISC Loading…
40
models/templates: add mistralai/Mistral-Small-3.1-24B-Instruct-2503 template with tool calling support
#14148 opened Jun 12, 2025 by bretello Loading…
3
tests : add test-model-random help wanted Extra attention is needed testing Everything test related
#14139 opened Jun 12, 2025 by compilade • Draft
4 of 16 tasks
2
ggml: aarch64: Implement SVE Kernels for Int 8 Quantization ggml changes relating to the ggml tensor library for machine learning
#14117 opened Jun 11, 2025 by Vithulep Loading…
3
scripts: Fix remote option in Windows (#14102) python python script changes
#14100 opened Jun 10, 2025 by pqnet Loading…
1
6
server: add model alias presets examples python python script changes server
#14083 opened Jun 9, 2025 by am17an Loading…
1
1
llama: automatically set runtime parameters such as --n-gpu-layers to fit VRAM ggml changes relating to the ggml tensor library for machine learning
#14067 opened Jun 8, 2025 by JohannesGaessler • Draft
16
webui: add server info to chat message examples server
#14065 opened Jun 8, 2025 by am17an Loading…
1
9
ggml-cpu: optimise assembly calls for hsum on s390x
#14037 opened Jun 5, 2025 by taronaeo Loading…
1
cpu: Update RISC-V condition to require GCC version 14 or higher ggml changes relating to the ggml tensor library for machine learning
#14032 opened Jun 5, 2025 by Ghosts381937 Loading…
llama : support qwen3 rerank and embeddings examples python python script changes server
#14029 opened Jun 5, 2025 by ngxson Loading…
1
39
ggml-cpu: fix uncaught underscore terminators for s390x ggml changes relating to the ggml tensor library for machine learning
#14023 opened Jun 5, 2025 by taronaeo Loading…
server: Enable mtmd in llama-server /completion endpoint examples server
#14016 opened Jun 4, 2025 by 92MING Loading…
1
llama: Attempt to add ModernBert model Model specific python python script changes
#14014 opened Jun 4, 2025 by huydt84 Loading…
74
ProTip! Updated in the last three days: updated:>2025-06-13.