Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
49,753 workflow run results
49,753 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Vulkan: Fix minor debug mode issues Server #16956: Pull request #14899 synchronize by 0cc4m
1h 6m 3s 0cc4m/vulkan-debug-fixes
0cc4m/vulkan-debug-fixes
1h 6m 3s
Vulkan: Fix minor debug mode issues CI #25556: Pull request #14899 synchronize by 0cc4m
2h 31m 23s 0cc4m/vulkan-debug-fixes
0cc4m/vulkan-debug-fixes
2h 31m 23s
Vulkan: Fix minor debug mode issues EditorConfig Checker #28682: Pull request #14899 synchronize by 0cc4m
50m 1s 0cc4m/vulkan-debug-fixes
0cc4m/vulkan-debug-fixes
50m 1s
vulkan: remove broken check_results GGML_OP_SET_ROWS support Python check requirements.txt #3889: Commit 573670b pushed by 0cc4m
33m 48s 0cc4m/vulkan-debug-fixes
0cc4m/vulkan-debug-fixes
33m 48s
vulkan: remove broken check_results GGML_OP_SET_ROWS support Update Operations Documentation #45: Commit 573670b pushed by 0cc4m
51m 44s 0cc4m/vulkan-debug-fixes
0cc4m/vulkan-debug-fixes
51m 44s
vulkan: remove broken check_results GGML_OP_SET_ROWS support Python Type-Check #3658: Commit 573670b pushed by 0cc4m
53m 15s 0cc4m/vulkan-debug-fixes
0cc4m/vulkan-debug-fixes
53m 15s
Vulkan: Fix minor debug mode issues Pull Request Labeler #14199: Pull request #14899 synchronize by 0cc4m
39m 35s
39m 35s
Added dynamic context size. This is perfect for servers running llama models as a service. Pull Request Labeler #14198: Pull request #13295 synchronize by J4e6eR
47m 30s
47m 30s
OpenCL: add initial FA support EditorConfig Checker #28680: Pull request #14987 opened by rmatif
47m 8s rmatif:opencl-add-fa
rmatif:opencl-add-fa
47m 8s
OpenCL: add initial FA support Server #16954: Pull request #14987 opened by rmatif
1h 24m 39s rmatif:opencl-add-fa
rmatif:opencl-add-fa
1h 24m 39s
OpenCL: add initial FA support CI #25554: Pull request #14987 opened by rmatif
1h 31m 24s rmatif:opencl-add-fa
rmatif:opencl-add-fa
1h 31m 24s
OpenCL: add initial FA support Pull Request Labeler #14197: Pull request #14987 opened by rmatif
1h 12m 2s
1h 12m 2s
server : implement universal assisted decoding (#12635) EditorConfig Checker #28679: Commit 94933c8 pushed by CISC
33m 14s master
master
33m 14s
server : implement universal assisted decoding (#12635) Server #16953: Commit 94933c8 pushed by CISC
1h 44m 13s master
master
1h 44m 13s
server : implement universal assisted decoding (#12635) Release #575: Commit 94933c8 pushed by CISC
2h 11m 58s master
master
2h 11m 58s
server : implement universal assisted decoding (#12635) CI #25553: Commit 94933c8 pushed by CISC
8h 49m 57s master
master
8h 49m 57s
model: Add support for GLM 4.5 family of models (#14921) Pull Request Labeler #14196: Pull request #14939 synchronize by sammcj
46m 27s
46m 27s
llama : merge build_moe_ffn_from_probs function into build_moe_ffn (#… EditorConfig Checker #28677: Commit c1dacaa pushed by CISC
13m 35s master
master
13m 35s
llama : merge build_moe_ffn_from_probs function into build_moe_ffn (#… Server #16951: Commit c1dacaa pushed by CISC
1h 43m 21s master
master
1h 43m 21s
llama : merge build_moe_ffn_from_probs function into build_moe_ffn (#… Release #574: Commit c1dacaa pushed by CISC
2h 21m 54s master
master
2h 21m 54s
llama : merge build_moe_ffn_from_probs function into build_moe_ffn (#… CI #25551: Commit c1dacaa pushed by CISC
8h 6m 29s master
master
8h 6m 29s
server : add openai-style logit_bias support (#14946) Server #16950: Commit a9f77a8 pushed by CISC
1h 17m 18s master
master
1h 17m 18s
server : add openai-style logit_bias support (#14946) EditorConfig Checker #28676: Commit a9f77a8 pushed by CISC
3m 0s master
master
3m 0s
server : add openai-style logit_bias support (#14946) flake8 Lint #19011: Commit a9f77a8 pushed by CISC
10m 24s master
master
10m 24s
server : add openai-style logit_bias support (#14946) Python Type-Check #3656: Commit a9f77a8 pushed by CISC
7m 34s master
master
7m 34s