Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
6,382 workflow run results
6,382 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[CANN]Support OP MUL_MAT_ID CI #22477: Pull request #13042 synchronize by noemotiovon
3m 22s noemotiovon:opt_support
noemotiovon:opt_support
3m 22s
llama-bench : add defrag-thold, check for invalid ranges (#13487) CI #22476: Commit cf0a43b pushed by slaren
54m 44s master
master
54m 44s
opencl: remove unnecessary assert for add (#13257) CI #22475: Commit f0d46ef pushed by max-krasnyansky
46m 37s master
master
46m 37s
llama-bench : add defrag-thold, check for invalid ranges CI #22474: Pull request #13487 opened by slaren
51m 9s sl/fix-llama-bench-zero-exp
sl/fix-llama-bench-zero-exp
51m 9s
quantize: improve pattern matching for allowed tensors CI #22473: Pull request #13033 synchronize by EAddario
1h 15m 2s EAddario:quantize
EAddario:quantize
1h 15m 2s
kv-cache : add SWA support CI #22472: Pull request #13194 synchronize by ggerganov
53m 8s gg/swa
gg/swa
53m 8s
kv-cache : add SWA support CI #22471: Pull request #13194 synchronize by ggerganov
9m 14s gg/swa
gg/swa
9m 14s
kv-cache : add SWA support CI #22470: Pull request #13194 synchronize by ggerganov
18m 29s gg/swa
gg/swa
18m 29s
kv-cache : add SWA support CI #22469: Pull request #13194 synchronize by ggerganov
10m 20s gg/swa
gg/swa
10m 20s
sycl: use oneDNN for matrices multiplication CI #22468: Pull request #12972 synchronize by lslusarczyk
2h 15m 35s lslusarczyk:todnn
lslusarczyk:todnn
2h 15m 35s
clip : cap max image size 1024 for qwen vl model (#13478) CI #22467: Commit de4c07f pushed by ngxson
3h 53m 23s master
master
3h 53m 23s
sycl : Overcoming workaround for mmap() allocation on Windows CI #22466: Pull request #13482 opened by s-Nick
1h 51m 9s s-Nick:add_win_mmap_support
s-Nick:add_win_mmap_support
1h 51m 9s
llama/ggml: add LLM training support (#10544) CI #22464: Commit 10d2af0 pushed by JohannesGaessler
3h 20m 25s master
master
3h 20m 25s
CUDA: update build CTK version to 12.8 CI #22463: Pull request #13360 synchronize by thevishalagarwal
1h 50m 56s thevishalagarwal:github-workflow/update-cuda-12.8
thevishalagarwal:github-workflow/update-cuda-12.8
1h 50m 56s
context : fix state io for memory-less contexts (#13470) CI #22462: Commit 064cc59 pushed by ggerganov
3h 6m 26s master
master
3h 6m 26s
server : allow content to be null in oaicompat_completion_params_pars… CI #22461: Commit 91159ee pushed by CISC
2h 34m 43s master
master
2h 34m 43s
CUDA: update build CTK version to 12.8 CI #22460: Pull request #13360 synchronize by thevishalagarwal
42m 15s thevishalagarwal:github-workflow/update-cuda-12.8
thevishalagarwal:github-workflow/update-cuda-12.8
42m 15s
kv-cache : add SWA support CI #22459: Pull request #13194 synchronize by ggerganov
1h 32m 10s gg/swa
gg/swa
1h 32m 10s
kv-cache : add SWA support CI #22458: Pull request #13194 synchronize by ggerganov
21m 50s gg/swa
gg/swa
21m 50s
llama-bench : accept ranges for integer parameters (#13410) CI #22457: Commit 22cdab3 pushed by slaren
2h 11m 45s master
master
2h 11m 45s
ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel (#13053) CI #22456: Commit a71a407 pushed by slaren
1h 49m 38s master
master
1h 49m 38s
clip : cap max image size 1024 for qwen vl model CI #22455: Pull request #13478 opened by ngxson
1h 10m 34s ngxson:xsn/mtmd_qwen2vl_reduce_img_size
ngxson:xsn/mtmd_qwen2vl_reduce_img_size
1h 10m 34s
Allow content null for tool call CI #22454: Pull request #13477 opened by anudit
1h 3m 21s anudit:master
anudit:master
1h 3m 21s
llama : try loading tensors with pre-computed hashes CI #22453: Pull request #13106 synchronize by rgerganov
2h 8m 35s rgerganov:rpc-load-tensor
rgerganov:rpc-load-tensor
2h 8m 35s
llama/ggml: add LLM training support CI #22452: Pull request #10544 synchronize by JohannesGaessler
2h 12m 8s JohannesGaessler:llama-opt-3
JohannesGaessler:llama-opt-3
2h 12m 8s