Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
1,123 Open 11,671 Closed
1,123 Open 11,671 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

server: add --no-sleep flag for GPU heartbeat on headless GPUs CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning server SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language Vulkan Issues specific to the Vulkan backend
#25214 opened Jul 1, 2026 by johnkarlhill Loading…
1
rocm: fix mmap loading of large models CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning
#25212 opened Jul 1, 2026 by pwilkin Member Loading…
1
Optimize RWKV7 inference by fusing some graph operators Apple Metal https://en.wikipedia.org/wiki/Metal_(API) CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning model Model specific SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related Vulkan Issues specific to the Vulkan backend
#25206 opened Jul 1, 2026 by MollySophia Collaborator • Draft
1
sycl: add GGML_SYCL_FATTN_VEC_NTHREADS build option ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#25205 opened Jul 1, 2026 by Titaniumtown Loading…
1
llama: fix quantized kv-cache for dsv4 model Model specific
#25202 opened Jul 1, 2026 by am17an Contributor Loading…
2
llama-cli: fix passing chat_template_kwargs and reasoning_format params examples
#25201 opened Jul 1, 2026 by percontation Contributor Loading…
ggml-cpu: Enable tiled matmul on AIX ggml changes relating to the ggml tensor library for machine learning
#25199 opened Jul 1, 2026 by shalinib-ibm Contributor Loading…
1
vulkan: disable async transfer queue on amdvlk (mitigate MoE partial-offload crash) ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#25196 opened Jul 1, 2026 by liminfei-amd Contributor Loading…
1 task done
5
vulkan: Remove crash guard for Intel GPU ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#25192 opened Jul 1, 2026 by rillomas Contributor • Draft
openvino: fix SWA mask detection for long prompts ggml changes relating to the ggml tensor library for machine learning OpenVINO
#25189 opened Jul 1, 2026 by zlma7001 Loading…
CUDA/HIP: add Q2_0 (PrismML ternary 1.58-bit) support CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning
#25188 opened Jul 1, 2026 by The-Monk • Draft
1
spec: add backend sampling for DFlash
#25180 opened Jun 30, 2026 by ruixiang63 Member • Draft
tests: Source-level separation between llama.cpp and ggml testing Everything test related
#25179 opened Jun 30, 2026 by ckastner Collaborator Loading…
1
metal: add col2im_1d op (f32/f16/bf16) Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#25176 opened Jun 30, 2026 by ServeurpersoCom Contributor Loading…
spec: add DSpark speculative decoding conversion model Model specific testing Everything test related
#25173 opened Jun 30, 2026 by wjinxu Loading…
22
grammar : recognize '|' at start of continuation line testing Everything test related
#25170 opened Jun 30, 2026 by o7si Contributor Loading…
1
hexagon: allow dflash lm-head offload experiment examples ggml changes relating to the ggml tensor library for machine learning Hexagon model Model specific
#25166 opened Jun 30, 2026 by Salanfeng Loading…
Add support for Laguna XS.2 & M.1 conversion CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning model Model specific testing Everything test related
#25165 opened Jun 30, 2026 by joerowell Loading…
20
ggml : fix wrong transpose function for int16 data ggml changes relating to the ggml tensor library for machine learning
#25161 opened Jun 30, 2026 by I3eg1nner Loading…
cuda: fix crash when querying memory on device with no free memory. CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning
#25157 opened Jun 30, 2026 by cphlipot Loading…
1
11
ggml: imatrix-aware NVFP4 quantization (scale search) + wire NVFP4 ftype examples ggml changes relating to the ggml tensor library for machine learning
#25153 opened Jun 30, 2026 by avifenesh Loading…
common, server : preserve HF file for cached models server
#25152 opened Jun 29, 2026 by mrexodia Loading…
CUDA: add COL2IM_1D op CUDA Related to the CUDA backend documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning
#25151 opened Jun 29, 2026 by Ssamdeman Loading…
4
speculative: fix MTP draft crash on vision inputs
#25144 opened Jun 29, 2026 by ServeurpersoCom Contributor Loading…
1
2
ui: strip path and weight extension from model id in single model mode server/ui
#25137 opened Jun 29, 2026 by ServeurpersoCom Contributor Loading…
ProTip! Filter pull requests by the default branch with base:master.