Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
36,057 workflow run results
36,057 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

imatrix: add option to display importance score statistics for a given imatrix file Server #14330: Pull request #12718 synchronize by EAddario
9m 39s EAddario:imatrix
EAddario:imatrix
9m 39s
imatrix: add option to display importance score statistics for a given imatrix file Pull Request Labeler #11607: Pull request #12718 synchronize by EAddario
15s
15s
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) Pull Request Labeler #11606: Pull request #13784 opened by ngxson
12s
12s
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) flake8 Lint #18263: Pull request #13784 opened by ngxson
18s ngxson:xsn/qwen25omni
ngxson:xsn/qwen25omni
18s
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) Python Type-Check #2768: Pull request #13784 opened by ngxson
2m 11s ngxson:xsn/qwen25omni
ngxson:xsn/qwen25omni
2m 11s
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) EditorConfig Checker #25770: Pull request #13784 opened by ngxson
20s ngxson:xsn/qwen25omni
ngxson:xsn/qwen25omni
20s
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) Python check requirements.txt #3158: Pull request #13784 opened by ngxson
3m 14s ngxson:xsn/qwen25omni
ngxson:xsn/qwen25omni
3m 14s
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) CI #22932: Pull request #13784 opened by ngxson
18m 15s ngxson:xsn/qwen25omni
ngxson:xsn/qwen25omni
18m 15s
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) Server #14329: Pull request #13784 opened by ngxson
10m 55s ngxson:xsn/qwen25omni
ngxson:xsn/qwen25omni
10m 55s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) CI #22931: Pull request #13771 synchronize by ochafik
49m 23s ochafik:enable-thinking
ochafik:enable-thinking
49m 23s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) Server #14328: Pull request #13771 synchronize by ochafik
15m 32s ochafik:enable-thinking
ochafik:enable-thinking
15m 32s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) Python Type-Check #2767: Pull request #13771 synchronize by ochafik
1m 29s ochafik:enable-thinking
ochafik:enable-thinking
1m 29s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) EditorConfig Checker #25769: Pull request #13771 synchronize by ochafik
21s ochafik:enable-thinking
ochafik:enable-thinking
21s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) flake8 Lint #18262: Pull request #13771 synchronize by ochafik
23s ochafik:enable-thinking
ochafik:enable-thinking
23s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) Pull Request Labeler #11605: Pull request #13771 synchronize by ochafik
15s
15s
vulkan: mark IM2COL as supporting non-contig CI #22930: Pull request #13783 opened by jeffbolznv
58m 8s jeffbolznv:im2col_noncontig
jeffbolznv:im2col_noncontig
58m 8s
vulkan: mark IM2COL as supporting non-contig EditorConfig Checker #25768: Pull request #13783 opened by jeffbolznv
20s jeffbolznv:im2col_noncontig
jeffbolznv:im2col_noncontig
20s
vulkan: mark IM2COL as supporting non-contig Server #14327: Pull request #13783 opened by jeffbolznv
10m 58s jeffbolznv:im2col_noncontig
jeffbolznv:im2col_noncontig
10m 58s
vulkan: mark IM2COL as supporting non-contig Pull Request Labeler #11604: Pull request #13783 opened by jeffbolznv
15s
15s
kv-cache : refactor + add llama_memory_state_i Server #14326: Pull request #13746 synchronize by ggerganov
10m 49s gg/kv-cache-simplify-part3
gg/kv-cache-simplify-part3
10m 49s
kv-cache : refactor + add llama_memory_state_i CI #22929: Pull request #13746 synchronize by ggerganov
52m 54s gg/kv-cache-simplify-part3
gg/kv-cache-simplify-part3
52m 54s
kv-cache : refactor + add llama_memory_state_i EditorConfig Checker #25767: Pull request #13746 synchronize by ggerganov
20s gg/kv-cache-simplify-part3
gg/kv-cache-simplify-part3
20s
kv-cache : refactor + add llama_memory_state_i Pull Request Labeler #11603: Pull request #13746 synchronize by ggerganov
14s
14s
server: args for draft model cache types (#11200) EditorConfig Checker #25766: Pull request #13782 opened by aa956
2m 49s aa956:server-parameter-draft-cache-type
aa956:server-parameter-draft-cache-type
2m 49s
server: args for draft model cache types (#11200) CI #22928: Pull request #13782 opened by aa956
1h 22m 38s aa956:server-parameter-draft-cache-type
aa956:server-parameter-draft-cache-type
1h 22m 38s
ProTip! You can narrow down the results and go further in time using created:<2025-05-25 or the other filters available.