Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
51,446 workflow run results
51,446 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add support for CogVLM model Check Pre-Tokenizer Hashes #4: Pull request #15002 synchronize by Tianyue-Zhao
31s Tianyue-Zhao:cogvlm_support
Tianyue-Zhao:cogvlm_support
31s
Add support for CogVLM model EditorConfig Checker #28781: Pull request #15002 synchronize by Tianyue-Zhao
20s Tianyue-Zhao:cogvlm_support
Tianyue-Zhao:cogvlm_support
20s
Add support for CogVLM model flake8 Lint #19046: Pull request #15002 synchronize by Tianyue-Zhao
21s Tianyue-Zhao:cogvlm_support
Tianyue-Zhao:cogvlm_support
21s
Add support for CogVLM model Python Type-Check #3698: Pull request #15002 synchronize by Tianyue-Zhao
2m 13s Tianyue-Zhao:cogvlm_support
Tianyue-Zhao:cogvlm_support
2m 13s
Add support for CogVLM model Python check requirements.txt #3912: Pull request #15002 synchronize by Tianyue-Zhao
3m 25s Tianyue-Zhao:cogvlm_support
Tianyue-Zhao:cogvlm_support
3m 25s
Add support for CogVLM model CI #25635: Pull request #15002 synchronize by Tianyue-Zhao
1h 2m 13s Tianyue-Zhao:cogvlm_support
Tianyue-Zhao:cogvlm_support
1h 2m 13s
Add support for CogVLM model Pull Request Labeler #14278: Pull request #15002 synchronize by Tianyue-Zhao
9s
9s
CUDA: use mma FA kernel for gqa > 4 on RTX 4000 (#15035) EditorConfig Checker #28780: Commit 03d4698 pushed by JohannesGaessler
28m 34s master
master
28m 34s
CUDA: use mma FA kernel for gqa > 4 on RTX 4000 (#15035) CI #25634: Commit 03d4698 pushed by JohannesGaessler
1h 46m 48s master
master
1h 46m 48s
CUDA: use mma FA kernel for gqa > 4 on RTX 4000 (#15035) Server #17040: Commit 03d4698 pushed by JohannesGaessler
38m 17s master
master
38m 17s
CUDA: use mma FA kernel for gqa > 4 on RTX 4000 (#15035) Release #599: Commit 03d4698 pushed by JohannesGaessler
53m 24s master
master
53m 24s
cuda: make im2col a little faster (#15025) EditorConfig Checker #28779: Commit 3303c19 pushed by ggerganov
50m 8s master
master
50m 8s
cuda: make im2col a little faster (#15025) CI #25633: Commit 3303c19 pushed by ggerganov
1h 54m 34s master
master
1h 54m 34s
cuda: make im2col a little faster (#15025) Server #17039: Commit 3303c19 pushed by ggerganov
47m 35s master
master
47m 35s
cuda: make im2col a little faster (#15025) Release #598: Commit 3303c19 pushed by ggerganov
1h 12m 45s master
master
1h 12m 45s
llama : enable LLAMA_SET_ROWS=1 by default (#14959) Server #17038: Commit a4569c4 pushed by ggerganov
36m 52s master
master
36m 52s
llama : enable LLAMA_SET_ROWS=1 by default (#14959) CI #25632: Commit a4569c4 pushed by ggerganov
1h 28m 55s master
master
1h 28m 55s
llama : enable LLAMA_SET_ROWS=1 by default (#14959) EditorConfig Checker #28778: Commit a4569c4 pushed by ggerganov
44m 21s master
master
44m 21s
llama : enable LLAMA_SET_ROWS=1 by default (#14959) Release #597: Commit a4569c4 pushed by ggerganov
1h 4m 26s master
master
1h 4m 26s
cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1 (#15038) CI #25631: Commit 15e92fd pushed by ggerganov
1h 4m 29s master
master
1h 4m 29s
cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1 (#15038) Release #596: Commit 15e92fd pushed by ggerganov
52m 20s master
master
52m 20s
cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1 (#15038) EditorConfig Checker #28777: Commit 15e92fd pushed by ggerganov
44m 2s master
master
44m 2s
cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1 (#15038) Server #17037: Commit 15e92fd pushed by ggerganov
31m 38s master
master
31m 38s
kv-cache : skip alignment of n_stream in kv-cache log msg [no ci] Pull Request Labeler #14277: Pull request #15040 opened by danbev
21m 50s
21m 50s
cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1 CI #25630: Pull request #15038 synchronize by ggerganov
1h 23m 47s gg/cuda-sycl-mm-batched-fix
gg/cuda-sycl-mm-batched-fix
1h 23m 47s