Skip to content

Actions: AD2605/llama.cpp

Actions

EditorConfig Checker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
editorconfig.yml
28 workflow runs
28 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
devops: switch to using ubuntu-22.04-s390x image (#16302) EditorConfig Checker #28: Commit 0124ac9 pushed by AD2605
22s master
master
22s
ci : enable Vulkan workflow on Mac (#16194) EditorConfig Checker #27: Commit 0889589 pushed by AD2605
18s master
master
18s
chat : Seed OSS thinking + tool call support (#15552) EditorConfig Checker #26: Commit 60e5eee pushed by AD2605
21s master
master
21s
ggml : prevent integer overflow in gguf tensor size calculation (#14595) EditorConfig Checker #25: Commit 26a48ad pushed by AD2605
4m 3s master
master
4m 3s
CANN: update aclnnGroupedMatmulV2 to aclnnGroupedMatmulV3 (#14411) EditorConfig Checker #24: Commit 343b6e9 pushed by AD2605
18s master
master
18s
Add Conv2d for CPU (#14388) EditorConfig Checker #23: Commit 0a5a3b5 pushed by AD2605
18s master
master
18s
opencl: ref count ggml_backend_opencl_context and refactor profilin… EditorConfig Checker #22: Commit 73e53dc pushed by AD2605
19s master
master
19s
ggml : fix repack work size for mul_mat_id (#14292) EditorConfig Checker #21: Commit d27b3ca pushed by AD2605
17s master
master
17s
ggml-cpu : remove the weak alias trick (#14221) EditorConfig Checker #20: Commit 860a9e4 pushed by AD2605
26s master
master
26s
webui: fix sidebar being covered by main content (#14082) EditorConfig Checker #19: Commit dc0623f pushed by AD2605
20s master
master
20s
convert : fix tensor naming conflict for llama 4 vision (#13836) EditorConfig Checker #18: Commit 26b79b6 pushed by AD2605
22s master
master
22s
sampling : make sure samplers return at least 1 token (#13822) EditorConfig Checker #17: Commit f9cd683 pushed by AD2605
18s master
master
18s
llama : allow custom list of swa_layers (#13726) EditorConfig Checker #16: Commit 8a2afb7 pushed by AD2605
18s master
master
18s
sycl: disable reorder for sycl mulmat (#13536) EditorConfig Checker #15: Commit 4245e62 pushed by AD2605
3m 35s master
master
3m 35s
mtmd : add vision support for llama 4 (#13282) EditorConfig Checker #14: Commit 92ecdcc pushed by AD2605
15s master
master
15s
CANN: Support MOE Model MUL_MAT_ID (#13042) EditorConfig Checker #13: Commit 33d7aed pushed by AD2605
16s master
master
16s
server : proper error handling for missing elements in messages array… EditorConfig Checker #12: Commit c753d7b pushed by AD2605
31s master
master
31s
clip : cap max image size 1024 for qwen vl model (#13478) EditorConfig Checker #11: Commit de4c07f pushed by AD2605
17s master
master
17s
metal : optimize MoE for large batches (#13388) EditorConfig Checker #10: Commit 611aa91 pushed by AD2605
1m 50s master
master
1m 50s
server : (webui) fix a very small misalignment (#13387) EditorConfig Checker #9: Commit ee01d71 pushed by AD2605
4m 37s master
master
4m 37s
docker : disable arm64 and intel images (#13356) EditorConfig Checker #8: Commit 814f795 pushed by AD2605
15s master
master
15s
llama : deci : support ffn-free with attention (#13296) EditorConfig Checker #7: Commit bc4e112 pushed by AD2605
15s master
master
15s
clip : fix confused naming ffn_up and ffn_down (#13290) EditorConfig Checker #6: Commit 5215b91 pushed by AD2605
18s master
master
18s
llama-chat : reset glmedge chat template (#13253) EditorConfig Checker #5: Commit 2af6880 pushed by AD2605
16s master
master
16s
ggml : fix trailing whitespaces (#0) EditorConfig Checker #4: Commit 87616f0 pushed by AD2605
3m 40s master
master
3m 40s