Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
785 Open 9,326 Closed
785 Open 9,326 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-cuda : fix UMA memory detection for HIP/ROCm on AMD APUs ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#20472 opened Mar 12, 2026 by hogeheer499-commits Loading…
1
2
common : fix SIGSEGV in _visit_pattern when quantifier follows empty seq
#20470 opened Mar 12, 2026 by pqhaz3925 Loading…
llama : fix pooling assertion crash in chunked GDN detection path examples python python script changes server
#20468 opened Mar 12, 2026 by ZeroV0LT Loading…
llama-bench: fix case where mmap and direct-io are turned on together examples
#20461 opened Mar 12, 2026 by taronaeo Loading…
Guard against sumq2 being 0 in IQ4_NL resulting in nan values ggml changes relating to the ggml tensor library for machine learning
#20460 opened Mar 12, 2026 by bartowski1182 Loading…
cmake : fix build warning when kleidiai is enabled ggml changes relating to the ggml tensor library for machine learning
#20457 opened Mar 12, 2026 by chaxu01 Loading…
2
metal : add NVFP4 quantization support Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#20456 opened Mar 12, 2026 by richarddd Loading…
1
[SYCL] add OP GATED_DELTA_NET to enhance to support Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#20455 opened Mar 12, 2026 by arthw Loading…
1
MoE expert profiling and REAP-based pruning tools examples python python script changes
#20454 opened Mar 12, 2026 by srossitto79 Loading…
4 tasks
2
native QLoRA training with reward-weighted SFT and GRPO examples ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#20453 opened Mar 12, 2026 by srossitto79 Loading…
5 tasks
3
vulkan: Slang flash attention shader ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#20451 opened Mar 12, 2026 by 0cc4m • Draft
1
CUDA: Optimize GDN PP perf ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#20449 opened Mar 12, 2026 by ORippler Loading…
CUDA: optimize GDN by hiding global memory loads ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#20448 opened Mar 12, 2026 by am17an Loading…
1 task done
3
common: Fix invalid iterator::end() dereference in common_regex
#20445 opened Mar 12, 2026 by rillomas Loading…
graph : remove redundant GDN state transposes Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning model Model specific Nvidia GPU Issues specific to Nvidia GPUs
#20443 opened Mar 12, 2026 by ggerganov Loading…
1 task done
1
4
convert : fix/suppress pyright errors python python script changes
#20442 opened Mar 12, 2026 by danbev Loading…
1
3
ggml-vulkan: disable transfer queue on UMA ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#20441 opened Mar 12, 2026 by RipleyTom Loading…
1
ggml: Improve NVFP4 vecdot error ggml changes relating to the ggml tensor library for machine learning
#20435 opened Mar 12, 2026 by michaelw9999 Loading…
3
CI: add hip quality check devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning python python script changes script Script related
#20430 opened Mar 11, 2026 by IMbackK • Draft
13
common/parser: add proper reasoning tag prefill reading documentation Improvements or additions to documentation examples server testing Everything test related
#20424 opened Mar 11, 2026 by pwilkin Loading…
7
llama : add fd-based model loading via llama_model_load_from_fd ( REWORK ) ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#20402 opened Mar 11, 2026 by Siddhesh2377 Loading…
ggml-cpu: Add get_rows support for Q6_K REPACK ggml changes relating to the ggml tensor library for machine learning
#20396 opened Mar 11, 2026 by Alcpz • Draft
common : add --sched-n-copies parameter for pipeline parallelism configuration examples ggml changes relating to the ggml tensor library for machine learning
#20395 opened Mar 11, 2026 by mxxm-t Loading…
1
kleidiai: add CPU feature detection to CI run script devops improvements to build systems and github actions python python script changes
#20394 opened Mar 11, 2026 by martin-klacer-arm Loading…
2
common : rework gpt-oss parser testing Everything test related
#20393 opened Mar 11, 2026 by aldehir Loading…
1
9
ProTip! Mix and match filters to narrow down what you’re looking for.