Skip to content

Actions: ggml-org/llama.cpp

Actions

Pull Request Labeler

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
labeler.yml
14,274 workflow runs
14,274 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

readme: add yzma Go bindings to list Pull Request Labeler #17837: Pull request #16651 opened by deadprogram
15s
15s
model: add Granite Hybrid models Pull Request Labeler #17836: Pull request #16635 synchronize by giuseppe
17s
17s
ggml-cpu: optimise rms_norm op Pull Request Labeler #17835: Pull request #16650 opened by taronaeo
15s
15s
model : add BailingMoeV2 support Pull Request Labeler #17834: Pull request #16063 synchronize by CISC
15s
15s
model : add BailingMoeV2 support Pull Request Labeler #17833: Pull request #16063 synchronize by CISC
21m 20s
21m 20s
metal : initial Metal4 tensor API support Pull Request Labeler #17832: Pull request #16634 synchronize by ggerganov
20s
20s
metal : initial Metal4 tensor API support Pull Request Labeler #17831: Pull request #16634 synchronize by ggerganov
19s
19s
metal : initial Metal4 tensor API support Pull Request Labeler #17830: Pull request #16634 synchronize by ggerganov
18s
18s
CUDA: fuse gate + up for mmvq, and mmvf Pull Request Labeler #17829: Pull request #16630 synchronize by am17an
16s
16s
feat(webui): improve LaTeX rendering with currency detection Pull Request Labeler #17828: Pull request #16508 synchronize by srogmann
1m 34s
1m 34s
CUDA: topk-moe: add optional parameter for gpt-oss Pull Request Labeler #17827: Pull request #16649 opened by am17an
2m 37s
2m 37s
model: add Granite Hybrid models Pull Request Labeler #17826: Pull request #16635 synchronize by giuseppe
15s
15s
webui: introduce OpenAI-compatible model selector in JSON payload Pull Request Labeler #17825: Pull request #16562 synchronize by ServeurpersoCom
18s
18s
Model: Qwen3 Next Pull Request Labeler #17824: Pull request #16095 synchronize by pwilkin
20s
20s
Model: Qwen3 Next Pull Request Labeler #17823: Pull request #16095 synchronize by pwilkin
19s
19s
Model: Qwen3 Next Pull Request Labeler #17822: Pull request #16095 synchronize by pwilkin
21s
21s
Model: Qwen3 Next Pull Request Labeler #17821: Pull request #16095 synchronize by pwilkin
16s
16s
devops: add s390x release binaries Pull Request Labeler #17820: Pull request #16648 opened by taronaeo
15s
15s
CUDA: use registers instead of smem in topk-moe Pull Request Labeler #17819: Pull request #16647 opened by am17an
18s
18s
CUDA: fuse gate + up for mmvq, and mmvf Pull Request Labeler #17818: Pull request #16630 synchronize by am17an
18s
18s
vulkan: Optimize SSM_SCAN Pull Request Labeler #17817: Pull request #16645 opened by jeffbolznv
2m 52s
2m 52s
CUDA: fuse gate + up for mmvq, and mmvf Pull Request Labeler #17816: Pull request #16630 synchronize by am17an
14s
14s
Model: Qwen3 Next Pull Request Labeler #17815: Pull request #16095 synchronize by pwilkin
45s
45s
Add experimental ggml-hexagon backend for the Hexagon NPU Pull Request Labeler #17814: Pull request #16547 synchronize by max-krasnyansky
17s
17s
sycl: use async memory allocation to fix crashes during graph recording Pull Request Labeler #17813: Pull request #16644 opened by mmichel11
18s
18s