Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
Clear current search query, filters, and sorts
613 Open 8,019 Closed
613 Open 8,019 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: Windows 7 compatibility build Compilation issues examples Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix server
#8208 opened Jun 29, 2024 by Zor-X-L Loading…
2 of 4 tasks
14 👎 1
llama : store non-RoPEd K cache demo Demonstrate some concept or idea, not intended to be merged
#3234 opened Sep 17, 2023 by ggerganov • Draft
11
vulkan : add dynamic VRAM heuristic for low-VRAM GPUs documentation Improvements or additions to documentation examples ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#17485 opened Nov 25, 2025 by cafeTechne Loading…
4
chat: add defensive IBM Granite Jinja compatibility (<tool_call> and <|tool_call|> support)
#16537 opened Oct 12, 2025 by ServeurpersoCom • Draft
1
2
--numa mirror: mirror model weights to every Numa node in the system Apple Metal https://en.wikipedia.org/wiki/Metal_(API) Ascend NPU issues specific to Ascend NPUs devops improvements to build systems and github actions examples ggml changes relating to the ggml tensor library for machine learning IBM zDNN issues specific to IBM zDNN Accelerator Nvidia GPU Issues specific to Nvidia GPUs OpenCL Issues specific to the OpenCL backend python python script changes SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related Vulkan Issues specific to the Vulkan backend
#16000 opened Sep 15, 2025 by dbsanfte • Draft
22
llama : add Xiaomi Mimo (with proper MTP - multi token predict) python python script changes
#13236 opened May 1, 2025 by ngxson • Draft
1
10
sgemm: reuse loaded vector in AVX dot product calculation ggml changes relating to the ggml tensor library for machine learning vibe-coded Created with heavy use of LLM assistants, requires human verification
#17648 opened Dec 1, 2025 by GermanAizek Loading…
tests(test-backend-ops): Test backend ops verbosity testing Everything test related
#17029 opened Nov 5, 2025 by gabe-l-hart Loading…
1
server: add support for local image path loading for server examples python python script changes server
#16874 opened Oct 30, 2025 by cchadowitz Loading…
15
webui: save model name with conversation history (#13570) examples server
#14192 opened Jun 15, 2025 by deepanshu2015 Loading…
3
CUDA & CPU: support F32 kernel type for CONV_TRANSPOSE_2D ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17094 opened Nov 8, 2025 by AgainstEntropy Loading…
15
ggml : enhance rel-pos and window ops with CUDA support ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17383 opened Nov 19, 2025 by bluebread Loading…
9
Add CUDA non-contiguous Unary Ops support build Compilation issues documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#14639 opened Jul 11, 2025 by YavorGIvanov Loading…
16
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…
Metal TQ2_0 Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#12485 opened Mar 20, 2025 by dmahurin Loading…
3
Fix convert script for non-hf GLM4 checkpoints python python script changes
#12992 opened Apr 17, 2025 by Tianyue-Zhao Loading…
2 of 4 tasks
Introduce Graph Profiler ggml changes relating to the ggml tensor library for machine learning
#9659 opened Sep 26, 2024 by max-krasnyansky Loading…
6
model : Fix marker placement for LFM2-VL in single turn llama-mtmd-cli examples
#17616 opened Nov 30, 2025 by tdakhran Loading…
14
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error examples
#15550 opened Aug 24, 2025 by EAddario • Draft
17
Add PagedAttention support (experimental, CUDA only) examples ggml changes relating to the ggml tensor library for machine learning model Model specific Nvidia GPU Issues specific to Nvidia GPUs server
#17579 opened Nov 28, 2025 by ericcurtin • Draft
6
mtmd : Support jinja in libmtmd (Only for QwenVL and Qwen Omni) examples
#14730 opened Jul 17, 2025 by alielmorsy Loading…
3
GGML: Fix leak of backend buffer memory address in RPC ggml changes relating to the ggml tensor library for machine learning
#14882 opened Jul 26, 2025 by struct Loading…
2
feat(batched): Add functionality to upload benchmark test results examples
#14811 opened Jul 22, 2025 by MengAiDev Loading…
cmake : set RPATH to $ORIGIN on Linux (#13740) build Compilation issues
#13741 opened May 24, 2025 by sunhaitao Loading…
12
Move page cache via mbind to prevent cross-NUMA access build Compilation issues
#13731 opened May 23, 2025 by vishalc-ibm Loading…
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.