Skip to content

Actions: EAddario/llama.cpp

Actions

EditorConfig Checker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
editorconfig.yml
10 workflow run results
10 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

clip : refactor, add image_manipulation and llava_uhd classes (#1… EditorConfig Checker #10: Commit 37b9f0d pushed by EAddario
19s master
master
19s
llama : recognize IBM Granite 3.3 FIM tokens (#12988) EditorConfig Checker #9: Commit 971f245 pushed by EAddario
35s master
master
35s
opencl: split ggml-opencl.cl into multiple files and cleanup (#12886) EditorConfig Checker #8: Commit 80f19b4 pushed by EAddario
17s master
master
17s
metal : add FA-vec kernels for head size 96 (#12952) EditorConfig Checker #7: Commit f8f820c pushed by EAddario
1m 26s master
master
1m 26s
CUDA/HIP: Share the same unified memory allocation logic. (#12934) EditorConfig Checker #6: Commit 84778e9 pushed by EAddario
2m 27s master
master
2m 27s
llama : DeepSeek V2/V3 MLA implementation (#12801) EditorConfig Checker #5: Commit daa4228 pushed by EAddario
1m 45s master
master
1m 45s
Add performance print for gemma3 in example (#12929) EditorConfig Checker #4: Commit d6d2c2a pushed by EAddario
18s master
master
18s
sync : ggml EditorConfig Checker #3: Commit 526739b pushed by EAddario
19s master
master
19s
ggml: disable CUDA graphs for unsupported DUP and CONT node types (#1… EditorConfig Checker #2: Commit 307bfa2 pushed by EAddario
17s master
master
17s
hellaswag: display estimated score confidence interval (#12797) EditorConfig Checker #1: Commit 4ccea21 pushed by EAddario
16s master
master
16s