Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
1,632 Open 13,531 Closed
1,632 Open 13,531 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-meta: resolve multi buffer views ggml changes relating to the ggml tensor library for machine learning
#29266 opened Sep 22, 2026 by 0cc4m Contributor Loading…
ggml-sycl : fix VMM pool pinning VRAM and collapse performance when the model does not fit ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#29265 opened Sep 22, 2026 by Asahi-Prv Contributor • Draft
ggml-cpu : yield in ggml_barrier after a short spin ggml changes relating to the ggml tensor library for machine learning
#29258 opened Sep 22, 2026 by joweeba • Draft
2
convert: add MiMo-V2.6 support conversion
#29257 opened Sep 22, 2026 by AesSedai Contributor Loading…
3
SVE Implementation of gemv q6 k 8x8 q8 k ggml changes relating to the ggml tensor library for machine learning
#29256 opened Sep 22, 2026 by abhijain1204fujitsu Contributor • Draft
1
[vulkan] Load F32 A matrix 2 at a time when its 2-aligned ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#29254 opened Sep 21, 2026 by TheBlueMatt Contributor Loading…
2
common: add --no-mmap-prefetch to skip MADV_WILLNEED for large models
#29250 opened Sep 21, 2026 by darkhipo • Draft
1
rfc: Memory eliding fusions AMD ZenDNN Issues related to the AMD ZenDNN backend Apple Metal https://en.wikipedia.org/wiki/Metal_(API) Ascend NPU issues specific to Ascend NPUs CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning Hexagon IBM zDNN issues specific to IBM zDNN Accelerator OpenCL Issues specific to the OpenCL backend OpenVINO SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language Vulkan Issues specific to the Vulkan backend WebGPU
#29247 opened Sep 21, 2026 by cwriter Contributor • Draft
sycl: add grouped MoE XMX GEMM ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#29245 opened Sep 21, 2026 by cwriter Contributor Loading…
jinja : parse unary +/- before variables jinja parser Issues related to the jinja parser testing Everything test related
#29244 opened Sep 21, 2026 by cs-fisha Loading…
1
5
sycl: FWHT kernels for block widths above 512 ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related
#29243 opened Sep 21, 2026 by bri-prism Contributor • Draft
common : strip matching quotes from INI preset values testing Everything test related
#29236 opened Sep 21, 2026 by cs-fisha Loading…
1 task done
1
1
HIP: bump HIP_VERSION requried for fp8 to avoid missing __hip_fp8_e4m3 support in 6.2 CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning
#29231 opened Sep 21, 2026 by IMbackK Contributor Loading…
1
cmake : allow repeated find_package calls for llama build Compilation issues examples
#29228 opened Sep 21, 2026 by miyanyan Contributor Loading…
model :support Gemma4 DSpark draft backbone conversion model Model specific
#29226 opened Sep 21, 2026 by hthadicherla Loading…
@ggerganov
5
kleidiai: add SME2 Q4_K and Q6_K matmul support ggml changes relating to the ggml tensor library for machine learning
#29219 opened Sep 21, 2026 by chaxu01 Collaborator Loading…
[SYCL] support new UT case for mul_mat_hadamard fp16 ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#29218 opened Sep 21, 2026 by arthw Contributor Loading…
server: fix router eviction races with the existing queue server
#29217 opened Sep 21, 2026 by ServeurpersoCom Contributor Loading…
1
vulkan: do not pin host memory past the host-visible heap budget ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#29213 opened Sep 21, 2026 by linxuhao Loading…
4
server: do not pass log file to children server
#29212 opened Sep 21, 2026 by dfriehs Contributor Loading…
llama-vocab : add "sophia" pre-tokenizer type devops improvements to build systems and github actions
#29211 opened Sep 21, 2026 by Arain119 Loading…
3
hexagon: optimize FA DMA mask cache ggml changes relating to the ggml tensor library for machine learning Hexagon
#29210 opened Sep 21, 2026 by jhen0409 Member Loading…
2
Hexagon f16 activation ops ggml changes relating to the ggml tensor library for machine learning Hexagon testing Everything test related
#29209 opened Sep 21, 2026 by cqderek Contributor • Draft
speculative : clamp draft context to n_ctx_train for unified KV
#29208 opened Sep 21, 2026 by nandan2003 Contributor Loading…
1 task done
1
1
cpu: add F16 SWIGLU_OAI reference implementation and F16 activation o… ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#29200 opened Sep 21, 2026 by cqderek Contributor Loading…
ProTip! Filter pull requests by the default branch with base:master.