Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
1,231 Open 12,157 Closed
1,231 Open 12,157 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

docs: Adapt conda-forge package name documentation Improvements or additions to documentation
#26229 opened Jul 28, 2026 by jjerphan Contributor Loading…
1
mimo2: add MTP draft support conversion model Model specific
#26228 opened Jul 28, 2026 by tnhnyzc Contributor Loading…
core : support output vocab size distinct from embedding vocab size conversion
#26226 opened Jul 28, 2026 by adithyab94 Contributor Loading…
2 tasks done
1
Proper fix for host buffer sync ggml changes relating to the ggml tensor library for machine learning
#26225 opened Jul 28, 2026 by pwilkin Member Loading…
metal: fix NaN in mul_mm_id when activations exceed f16 range Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#26223 opened Jul 28, 2026 by mdegans Contributor Loading…
1
2
server: abstract llama_memory calls to common_memory server
#26221 opened Jul 28, 2026 by ngxson Collaborator Loading…
5
convert : fix bytes_to_unicode import for transformers >= 5.15 conversion
#26217 opened Jul 28, 2026 by SolshineCode Loading…
2
vulkan: fix Raspberry Pi V3D WG≤256 / low-SMEM enablement ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#26214 opened Jul 28, 2026 by odilitime Loading…
3
server : add /slots endpoint action=clone_to (KV clone between slots) documentation Improvements or additions to documentation server
#26204 opened Jul 27, 2026 by solethais Loading…
2
HIP: MMQ Dispatch config modification - separation of RDNA3, 3.5 from 4 and tune 4. CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning
#26199 opened Jul 27, 2026 by Geramy Loading…
1
server: fix prompt cache entry selection and f_keep filter documentation Improvements or additions to documentation server
#26198 opened Jul 27, 2026 by q-g-j Loading…
1
@ggerganov
1
opencl: skip the Adreno KQ/KQV image kernels for multi-stream batches when FA is off ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#26189 opened Jul 27, 2026 by wanghqc Contributor Loading…
ggml-cpu: add -mavxvnni for clang-cl when GGML_AVX_VNNI is enabled ggml changes relating to the ggml tensor library for machine learning
#26187 opened Jul 27, 2026 by MaxCrazy1101 Loading…
1
model: add Kimi-K3 text model conversion model Model specific testing Everything test related
#26185 opened Jul 27, 2026 by pwilkin Member Loading…
22
feat: Add '--ignore-api-samplers' CLI flag to ignore API sampler settings server
#26182 opened Jul 27, 2026 by Sciguy429 Loading…
Support quantized kv cache for Minimax M3 model Model specific
#26180 opened Jul 27, 2026 by timkhronos Contributor Loading…
1
2
Add more benchmarks to llama-eval documentation Improvements or additions to documentation examples
#26174 opened Jul 27, 2026 by pwilkin Member Loading…
tests: add model resolution test on synthetic repo listings testing Everything test related
#26172 opened Jul 27, 2026 by ServeurpersoCom Contributor Loading…
ggml-cuda: Allow transpose-free gemmv computation CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#26171 opened Jul 27, 2026 by roberteg16 Loading…
ggml: add a scheduler sanitizer ggml changes relating to the ggml tensor library for machine learning
#26167 opened Jul 27, 2026 by am17an Contributor Loading…
3
[Model/VLA] Support MiniCPM-RobotManip build Compilation issues documentation Improvements or additions to documentation mtmd Related to multimodal functionality (video/image/audio) server
#26164 opened Jul 27, 2026 by tc-mb Contributor • Draft
opencl: bugfix: missing increment of ref_count in ggml_backend_opencl_init() ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#26162 opened Jul 27, 2026 by akleine Contributor Loading…
cuda: compact Blackwell NVFP4 MoE work scheduling (+10% to +15% prefill, NVFP4-only) CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning
#26159 opened Jul 27, 2026 by coder543 Contributor • Draft
2
ggml: add support for MXFP8 CPU conversion ggml changes relating to the ggml tensor library for machine learning
#26157 opened Jul 27, 2026 by michaelw9999 Contributor Loading…
mtmd: support multi-row batching for deepseek-ocr mtmd Related to multimodal functionality (video/image/audio)
#26154 opened Jul 26, 2026 by ngxson Collaborator Loading…
2
ProTip! What’s not been updated in a month: updated:<2026-06-28.