Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
10,934 workflow run results
10,934 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml : add CPU backend reference implementation (wip) CI #27633: Pull request #16004 synchronize by danbev
3h 41m 53s danbev:test-backend-ops-all-cpu-variants
danbev:test-backend-ops-all-cpu-variants
3h 41m 53s
Add resumable downloads for llama-server model loading CI #27631: Pull request #15963 synchronize by ericcurtin
3h 24m 28s resumable
resumable
3h 24m 28s
llama-run: Fix model download on Windows (#15988) CI #27630: Commit 28c39da pushed by ericcurtin
3h 39m 24s master
master
3h 39m 24s
SYCL: Add COUNT_EQUAL operator support CI #27628: Pull request #15991 synchronize by yael-works
2h 51m 1s yael-works:yael/count-equal
yael-works:yael/count-equal
2h 51m 1s
CUDA: some micro-optimizations in mmf.cuh for mul_mat_id (#15926) CI #27627: Commit 1062205 pushed by am17an
3h 13m 52s master
master
3h 13m 52s
metal : refactor + optimize v2 CI #27626: Pull request #15995 synchronize by ggerganov
2h 26m 51s gg/metal-refactor-and-optimize-v2
gg/metal-refactor-and-optimize-v2
2h 26m 51s
Add LLaDA-7b-MoE diffusion model CI #27625: Pull request #16003 synchronize by am17an
3h 12m 39s am17an:llada_moe
am17an:llada_moe
3h 12m 39s
CANN: Fix ggml_cann_set_device to avoid redundant device switches CI #27624: Pull request #15935 synchronize by noemotiovon
3h 15m 26s noemotiovon:set_device_opti
noemotiovon:set_device_opti
3h 15m 26s
ggml : add CPU backend reference implementation (wip) CI #27623: Pull request #16004 opened by danbev
1h 5m 53s danbev:test-backend-ops-all-cpu-variants
danbev:test-backend-ops-all-cpu-variants
1h 5m 53s
Feat: Apertus model implementation CI #27622: Pull request #15852 synchronize by pwilkin
2h 6m 20s pwilkin:apertus-implementation
pwilkin:apertus-implementation
2h 6m 20s
--numa mirror: mirror model weights to every Numa node in the system CI #27621: Pull request #16000 synchronize by dbsanfte
3h 15m 12s dbsanfte:numa-mirror
dbsanfte:numa-mirror
3h 15m 12s
Add LLaDA-7b-MoE diffusion model CI #27620: Pull request #16003 opened by am17an
28m 0s am17an:llada_moe
am17an:llada_moe
28m 0s
Feat: Apertus model implementation CI #27619: Pull request #15852 synchronize by pwilkin
7m 39s pwilkin:apertus-implementation
pwilkin:apertus-implementation
7m 39s
examples : support encoder-decoder models in the simple example CI #27617: Pull request #16002 opened by DamonFool
1h 15m 38s DamonFool:jf
DamonFool:jf
1h 15m 38s
SYCL: Add COUNT_EQUAL operator support CI #27615: Pull request #15991 synchronize by yael-works
1h 1m 47s yael-works:yael/count-equal
yael-works:yael/count-equal
1h 1m 47s
fix KLD percentile output (#15999) CI #27614: Commit a68f31e pushed by JohannesGaessler
1h 36m 24s master
master
1h 36m 24s
metal : refactor + optimize v2 CI #27611: Pull request #15995 synchronize by ggerganov
1h 7m 35s gg/metal-refactor-and-optimize-v2
gg/metal-refactor-and-optimize-v2
1h 7m 35s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error CI #27609: Pull request #15550 synchronize by EAddario
1h 27m 25s EAddario:quantize
EAddario:quantize
1h 27m 25s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices CI #27608: Pull request #14891 synchronize by EAddario
1h 9m 3s EAddario:imatrix
EAddario:imatrix
1h 9m 3s
fix KLD percentile output CI #27603: Pull request #15999 opened by ddh0
1h 6m 50s ddh0:fix-kld-percentile
ddh0:fix-kld-percentile
1h 6m 50s
CUDA: some micro-optimizations in mmf.cuh for mul_mat_id CI #27602: Pull request #15926 synchronize by am17an
1h 10m 50s am17an:mmf_opt_cuda
am17an:mmf_opt_cuda
1h 10m 50s
CANN: Fix ggml_cann_set_device to avoid redundant device switches CI #27601: Pull request #15935 synchronize by noemotiovon
14m 14s noemotiovon:set_device_opti
noemotiovon:set_device_opti
14m 14s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error CI #27599: Pull request #15550 synchronize by EAddario
1h 24m 44s EAddario:quantize
EAddario:quantize
1h 24m 44s
Feat: Apertus model implementation CI #27598: Pull request #15852 synchronize by pwilkin
1h 16m 20s pwilkin:apertus-implementation
pwilkin:apertus-implementation
1h 16m 20s
Feat: Apertus model implementation CI #27597: Pull request #15852 synchronize by pwilkin
14m 53s pwilkin:apertus-implementation
pwilkin:apertus-implementation
14m 53s