Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
5,695 workflow run results
5,695 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

clip : refactor, add image_manipulation and llava_uhd classes CI #21578: Pull request #13011 synchronize by ngxson
41m 35s ngxson:xsn/clip_refactor_img_manip
ngxson:xsn/clip_refactor_img_manip
41m 35s
clip : refactor, add image_manipulation and llava_uhd classes CI #21577: Pull request #13011 opened by ngxson
18m 32s ngxson:xsn/clip_refactor_img_manip
ngxson:xsn/clip_refactor_img_manip
18m 32s
llama-bench: enhance benchmark with improved token throughput measurements CI #21575: Pull request #12874 synchronize by thevishalagarwal
43m 46s thevishalagarwal:llama-bench/add-pp-tg-metrics
thevishalagarwal:llama-bench/add-pp-tg-metrics
43m 46s
SYCL: Refactor and enable FP16 in binary broadcast OPs CI #21574: Pull request #12975 synchronize by qnixsynapse
44m 58s binary-ops
binary-ops
44m 58s
mtmd : add methods to access mtmd_image_tokens (#12906) CI #21571: Commit b9154ec pushed by ngxson
52m 7s master
master
52m 7s
rpc : add RPC_CMD_HELLO (#12955) CI #21570: Commit 2db9ba1 pushed by rgerganov
44m 44s master
master
44m 44s
Nix portability improvements CI #21569: Pull request #13005 opened by hacker1024
4m 39s hacker1024:fix/nix-portability
hacker1024:fix/nix-portability
4m 39s
[CANN] Add the n_graph_splits performance metric to llama-bench. CI #21568: Pull request #12994 synchronize by bachelor-dou
41m 30s bachelor-dou:master
bachelor-dou:master
41m 30s
[CANN] Add the n_graph_splits performance metric to llama-bench. CI #21567: Pull request #12994 synchronize by bachelor-dou
5m 43s bachelor-dou:master
bachelor-dou:master
5m 43s
[SYCL][OPT] Fix reorder optimization for Q4_0 CI #21566: Pull request #13003 opened by NeoZhangJianyu
48m 30s NeoZhangJianyu:jianyuzh_fix_reorder
NeoZhangJianyu:jianyuzh_fix_reorder
48m 30s
[CANN] Add the n_graph_splits performance metric to llama-bench. CI #21564: Pull request #12994 synchronize by bachelor-dou
40m 48s bachelor-dou:master
bachelor-dou:master
40m 48s
[CANN] Add the n_graph_splits performance metric to llama-bench. CI #21563: Pull request #12994 synchronize by bachelor-dou
4m 33s bachelor-dou:master
bachelor-dou:master
4m 33s
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling CI #21562: Pull request #12995 synchronize by max-krasnyansky
41m 36s maxk/sched-prio-updates
maxk/sched-prio-updates
41m 36s
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling CI #21561: Pull request #12995 synchronize by max-krasnyansky
21m 48s maxk/sched-prio-updates
maxk/sched-prio-updates
21m 48s
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling CI #21560: Pull request #12995 synchronize by max-krasnyansky
2m 28s maxk/sched-prio-updates
maxk/sched-prio-updates
2m 28s
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling CI #21559: Pull request #12995 synchronize by max-krasnyansky
46m 29s maxk/sched-prio-updates
maxk/sched-prio-updates
46m 29s
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling CI #21558: Pull request #12995 synchronize by max-krasnyansky
3m 20s maxk/sched-prio-updates
maxk/sched-prio-updates
3m 20s
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling CI #21557: Pull request #12995 opened by max-krasnyansky
5m 28s maxk/sched-prio-updates
maxk/sched-prio-updates
5m 28s
kv-cache : separate recurrent vs non-recurrent impl CI #21556: Pull request #12799 synchronize by ggerganov
56m 16s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
56m 16s
graph : make FA compatible with MLA + add initial Metal kernels (#12953) CI #21555: Commit 2f74c35 pushed by ggerganov
55m 57s master
master
55m 57s
graph : make FA compatible with MLA + add initial Metal kernels CI #21554: Pull request #12953 synchronize by ggerganov
43m 0s gg/mla
gg/mla
43m 0s
ggml: Re-enable CUDA graphs in presence of CONT and DUP nodes (#12970) CI #21553: Commit 207c22e pushed by slaren
44m 4s master
master
44m 4s
kv-cache : separate recurrent vs non-recurrent impl CI #21552: Pull request #12799 synchronize by ggerganov
59m 20s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
59m 20s
CANN: Add support for async operator submission (#12864) CI #21551: Commit 7a395f6 pushed by hipudding
46m 28s master
master
46m 28s
kv-cache : separate recurrent vs non-recurrent impl CI #21550: Pull request #12799 synchronize by ggerganov
28m 17s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
28m 17s