Skip to content

Actions: ggml-org/llama.cpp

Actions

EditorConfig Checker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
editorconfig.yml
14,560 workflow runs
14,560 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Modern Bert Support EditorConfig Checker #33309: Pull request #15641 synchronize by ryan-mangeno
1h 23m 40s ryan-mangeno:modern-bert-support
ryan-mangeno:modern-bert-support
1h 23m 40s
server : support unified cache across slots EditorConfig Checker #33308: Pull request #16736 synchronize by ggerganov
1h 15m 1s gg/server-unified-slots
gg/server-unified-slots
1h 15m 1s
server : support unified cache across slots EditorConfig Checker #33307: Pull request #16736 synchronize by ggerganov
9m 1s gg/server-unified-slots
gg/server-unified-slots
9m 1s
server : remove n_past (#16818) EditorConfig Checker #33306: Commit b52edd2 pushed by ggerganov
1h 28m 21s master
master
1h 28m 21s
clip : use FA EditorConfig Checker #33305: Pull request #16837 synchronize by ggerganov
1h 39m 31s gg/clip-fa
gg/clip-fa
1h 39m 31s
clip : use FA EditorConfig Checker #33304: Pull request #16837 synchronize by ggerganov
4m 41s gg/clip-fa
gg/clip-fa
4m 41s
Update requirements-convert_legacy_llama.txt EditorConfig Checker #33303: Pull request #16866 opened by RodriMora
1h 6m 9s RodriMora:patch-2
RodriMora:patch-2
1h 6m 9s
cpu: introduce chunking for repack matmuls and enable matmul-id chunk… EditorConfig Checker #33302: Commit 517b717 pushed by max-krasnyansky
1h 23m 55s master
master
1h 23m 55s
common: fix typo in cli help text (#16864) EditorConfig Checker #33301: Commit 835e918 pushed by ggerganov
42m 16s master
master
42m 16s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) EditorConfig Checker #33300: Pull request #16817 synchronize by GittyBurstein
1h 16m 41s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
1h 16m 41s
model: add support for qwen3vl series (#16780) EditorConfig Checker #33298: Commit d261223 pushed by ngxson
6m 58s master
master
6m 58s
server: Allow for longer prompts in q URL parameter EditorConfig Checker #33297: Pull request #16862 opened by chansikpark
1h 19m 7s chansikpark:uri-max-length
chansikpark:uri-max-length
1h 19m 7s
CUDA: Volta tensor core support for MMF EditorConfig Checker #33296: Pull request #16843 synchronize by JohannesGaessler
53m 50s JohannesGaessler:cuda-mmf-volta-2
JohannesGaessler:cuda-mmf-volta-2
53m 50s
CANN: GGML_CANN_ACL_GRAPH works only if USE_ACL_GRAPH was enabled EditorConfig Checker #33295: Pull request #16861 opened by rauletorresc
Action required rauletorresc:patch-2
rauletorresc:patch-2
Action required
server : remove n_past EditorConfig Checker #33294: Pull request #16818 synchronize by ggerganov
43s gg/server-fix-n-past
gg/server-fix-n-past
43s
server : remove n_past EditorConfig Checker #33293: Pull request #16818 synchronize by ggerganov
56m 17s gg/server-fix-n-past
gg/server-fix-n-past
56m 17s
graph : reuse SSM graphs EditorConfig Checker #33292: Pull request #16490 synchronize by ggerganov
2h 3m 58s gg/graph-mamba-reuse
gg/graph-mamba-reuse
2h 3m 58s
CUDA: Remove unneded bias/gate dims in fused mmvq EditorConfig Checker #33291: Pull request #16858 synchronize by ORippler
50m 17s ORippler:osimons/remove_unneded_bias_gate_dims
ORippler:osimons/remove_unneded_bias_gate_dims
50m 17s
cpu: introduce chunking for flash attention (#16829) EditorConfig Checker #33290: Commit dcca0d3 pushed by ggerganov
50m 40s master
master
50m 40s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) EditorConfig Checker #33289: Pull request #16817 synchronize by yael-works
56m 27s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
56m 27s
ggml-cpu : inspect -march and -mcpu to found the CPU EditorConfig Checker #33287: Pull request #16333 synchronize by angt
56m 5s angt:inspect-march-and-mcpu-to-found-the-cpu
angt:inspect-march-and-mcpu-to-found-the-cpu
56m 5s
[model] add support for qwen3vl series EditorConfig Checker #33286: Pull request #16780 synchronize by JJJYmmm
30m 30s JJJYmmm:add_qwen3vl
JJJYmmm:add_qwen3vl
30m 30s
CUDA: Remove unneded bias/gate dims in fused mmvq EditorConfig Checker #33285: Pull request #16858 opened by ORippler
48m 1s ORippler:osimons/remove_unneded_bias_gate_dims
ORippler:osimons/remove_unneded_bias_gate_dims
48m 1s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) EditorConfig Checker #33284: Pull request #16817 synchronize by GittyBurstein
40m 46s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
40m 46s
server : remove n_past EditorConfig Checker #33283: Pull request #16818 synchronize by ngxson
21m 24s gg/server-fix-n-past
gg/server-fix-n-past
21m 24s