Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
43,009 workflow run results
43,009 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml-cpu: enable IBM NNPA Vector Intrinsics CI #24151: Pull request #14317 synchronize by taronaeo
7m 7s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
7m 7s
ggml-cpu: enable IBM NNPA Vector Intrinsics Server #15548: Pull request #14317 synchronize by taronaeo
6m 58s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
6m 58s
sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel Devices (#13973) Release #347: Commit 2bf9d53 pushed by Rbiessy
15m 26s master
master
15m 26s
sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel Devices (#13973) Server #15547: Commit 2bf9d53 pushed by Rbiessy
26m 23s master
master
26m 23s
sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel Devices (#13973) EditorConfig Checker #27111: Commit 2bf9d53 pushed by Rbiessy
5m 57s master
master
5m 57s
sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel Devices (#13973) CI #24150: Commit 2bf9d53 pushed by Rbiessy
50m 20s master
master
50m 20s
ggml-cpu: enable IBM NNPA Vector Intrinsics Server #15546: Pull request #14317 synchronize by taronaeo
4m 48s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
4m 48s
ggml-cpu: enable IBM NNPA Vector Intrinsics EditorConfig Checker #27110: Pull request #14317 synchronize by taronaeo
17s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
17s
ggml-cpu: enable IBM NNPA Vector Intrinsics CI #24149: Pull request #14317 synchronize by taronaeo
9m 22s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
9m 22s
ggml-cpu: enable IBM NNPA Vector Intrinsics Pull Request Labeler #12807: Pull request #14317 synchronize by taronaeo
10s
10s
ggml-cpu: enable IBM NNPA Vector Intrinsics CI #24148: Pull request #14317 synchronize by taronaeo
40m 32s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
40m 32s
ggml-cpu: enable IBM NNPA Vector Intrinsics EditorConfig Checker #27109: Pull request #14317 synchronize by taronaeo
7m 39s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
7m 39s
ggml-cpu: enable IBM NNPA Vector Intrinsics Server #15545: Pull request #14317 synchronize by taronaeo
23m 30s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
23m 30s
ggml-cpu: enable IBM NNPA Vector Intrinsics Pull Request Labeler #12806: Pull request #14317 synchronize by taronaeo
2m 17s
2m 17s
finetune: SGD optimizer, more CLI args Pull Request Labeler #12805: Pull request #13873 synchronize by graehl
2m 59s
2m 59s
finetune: SGD optimizer, more CLI args Pull Request Labeler #12804: Pull request #13873 synchronize by graehl
1m 10s
1m 10s
ggml-cpu: enable IBM NNPA Vector Intrinsics CI #24145: Pull request #14317 synchronize by taronaeo
53m 8s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
53m 8s
ggml-cpu: enable IBM NNPA Vector Intrinsics EditorConfig Checker #27106: Pull request #14317 synchronize by taronaeo
10m 27s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
10m 27s
ggml-cpu: enable IBM NNPA Vector Intrinsics Server #15542: Pull request #14317 synchronize by taronaeo
35m 15s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
35m 15s
ggml-cpu: enable IBM NNPA Vector Intrinsics Pull Request Labeler #12803: Pull request #14317 synchronize by taronaeo
5m 45s
5m 45s
llama : add high-throughput mode Server #15541: Pull request #14363 synchronize by ggerganov
15m 37s gg/llama-high-throughput
gg/llama-high-throughput
15m 37s
llama : add high-throughput mode Pull Request Labeler #12802: Pull request #14363 synchronize by ggerganov
14s
14s
llama : add high-throughput mode CI #24144: Pull request #14363 synchronize by ggerganov
1h 7m 34s gg/llama-high-throughput
gg/llama-high-throughput
1h 7m 34s
Changes sync Pull Request Labeler #12801: Pull request #14376 opened by esrakorkmz
14m 20s
14m 20s
llama : add high-throughput mode Server #15540: Pull request #14363 synchronize by ggerganov
18m 6s gg/llama-high-throughput
gg/llama-high-throughput
18m 6s