Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
30,428 workflow run results
30,428 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

SYCL: Fix im2col Pull Request Labeler #10079: Pull request #12910 opened by qnixsynapse
51s
51s
vulkan: Add bfloat16 support EditorConfig Checker #23992: Pull request #12554 synchronize by jeffbolznv
19s jeffbolznv:bfloat16_rebase
jeffbolznv:bfloat16_rebase
19s
vulkan: Add bfloat16 support Server #12779: Pull request #12554 synchronize by jeffbolznv
8m 18s jeffbolznv:bfloat16_rebase
jeffbolznv:bfloat16_rebase
8m 18s
vulkan: Add bfloat16 support CI #21404: Pull request #12554 synchronize by jeffbolznv
43m 6s jeffbolznv:bfloat16_rebase
jeffbolznv:bfloat16_rebase
43m 6s
vulkan: Add bfloat16 support Pull Request Labeler #10078: Pull request #12554 synchronize by jeffbolznv
10s
10s
Publish Docker image Publish Docker image #14915: Scheduled
1h 3m 46s master
master
1h 3m 46s
convert : write tensors in parallel flake8 Lint #17890: Pull request #12837 synchronize by compilade
17s compilade/parallel-convert
compilade/parallel-convert
17s
convert : write tensors in parallel EditorConfig Checker #23991: Pull request #12837 synchronize by compilade
18s compilade/parallel-convert
compilade/parallel-convert
18s
convert : write tensors in parallel Python Type-Check #2314: Pull request #12837 synchronize by compilade
1m 31s compilade/parallel-convert
compilade/parallel-convert
1m 31s
convert : write tensors in parallel Python check requirements.txt #2836: Pull request #12837 synchronize by compilade
3m 4s compilade/parallel-convert
compilade/parallel-convert
3m 4s
convert : write tensors in parallel Pull Request Labeler #10077: Pull request #12837 synchronize by compilade
14s
14s
gguf-py : use ThreadPoolExecutor when writing tensors Python Type-Check #2313: Commit 3fe362f pushed by compilade
1m 18s compilade/parallel-convert
compilade/parallel-convert
1m 18s
gguf-py : use ThreadPoolExecutor when writing tensors Python check requirements.txt #2835: Commit 3fe362f pushed by compilade
2m 47s compilade/parallel-convert
compilade/parallel-convert
2m 47s
SYCL: Add ROPE vision kernel CI #21403: Pull request #12887 synchronize by qnixsynapse
42m 23s rope_vision
rope_vision
42m 23s
SYCL: Add ROPE vision kernel EditorConfig Checker #23990: Pull request #12887 synchronize by qnixsynapse
16s rope_vision
rope_vision
16s
SYCL: Add ROPE vision kernel Server #12778: Pull request #12887 synchronize by qnixsynapse
9m 28s rope_vision
rope_vision
9m 28s
SYCL: Add ROPE vision kernel Pull Request Labeler #10076: Pull request #12887 synchronize by qnixsynapse
10s
10s
SYCL: Add ROPE vision kernel Python Type-Check #2312: Commit fd05898 pushed by qnixsynapse
1m 11s rope_vision
rope_vision
1m 11s
SYCL: Add ROPE vision kernel Python check requirements.txt #2834: Commit fd05898 pushed by qnixsynapse
3m 7s rope_vision
rope_vision
3m 7s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp CI #21402: Pull request #12326 synchronize by jeffzhou2000
10m 1s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
10m 1s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp EditorConfig Checker #23989: Pull request #12326 synchronize by jeffzhou2000
15s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
15s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp Server #12777: Pull request #12326 synchronize by jeffzhou2000
1m 42s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
1m 42s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp Pull Request Labeler #10075: Pull request #12326 synchronize by jeffzhou2000
11s
11s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp EditorConfig Checker #23988: Pull request #12326 synchronize by jeffzhou2000
16s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
16s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp Server #12776: Pull request #12326 synchronize by jeffzhou2000
1m 48s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
1m 48s
ProTip! You can narrow down the results and go further in time using created:<2025-04-12 or the other filters available.