Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
6,335 workflow run results
6,335 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : try loading tensors with pre-computed hashes CI #22340: Pull request #13106 synchronize by rgerganov
3h 50m 10s rgerganov:rpc-load-tensor
rgerganov:rpc-load-tensor
3h 50m 10s
kv-cache : add SWA support CI #22339: Pull request #13194 synchronize by ggerganov
3h 56m 2s gg/swa
gg/swa
3h 56m 2s
metal : optimize MoE for large batches (#13388) CI #22338: Commit 611aa91 pushed by ggerganov
4h 54m 47s master
master
4h 54m 47s
sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs CI #22337: Pull request #12858 synchronize by Alcpz
3h 5m 28s Alcpz:Alcpz/mmvq_q4_0_reorder
Alcpz:Alcpz/mmvq_q4_0_reorder
3h 5m 28s
CUDA: FA support for Deepseek (Ampere or newer) (#13306) CI #22336: Commit 0cf6725 pushed by JohannesGaessler
4h 51m 16s master
master
4h 51m 16s
sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs CI #22334: Pull request #12858 synchronize by Alcpz
53m 15s Alcpz:Alcpz/mmvq_q4_0_reorder
Alcpz:Alcpz/mmvq_q4_0_reorder
53m 15s
Add --no-op-offload to improve -ot pp perf in MoE models like llama4 400B CI #22333: Pull request #13386 synchronize by hjc4869
1h 59m 9s hjc4869:no_op_offload
hjc4869:no_op_offload
1h 59m 9s
llama : do not crash if there is no CPU backend (#13395) CI #22332: Commit 27ebfca pushed by slaren
3h 45m 6s master
master
3h 45m 6s
CUDA: fix crash on large batch size for MoE models (#13384) CI #22331: Commit 5c86c9e pushed by JohannesGaessler
3h 35m 44s master
master
3h 35m 44s
imatrix : Add --parse-special for enabling parsing of special tokens … CI #22330: Commit efb8b47 pushed by ngxson
3h 8m 46s master
master
3h 8m 46s
CUDA: FA support for Deepseek (Ampere or newer) CI #22329: Pull request #13306 synchronize by JohannesGaessler
1h 23m 36s JohannesGaessler:cuda-deepseek-fa-4
JohannesGaessler:cuda-deepseek-fa-4
1h 23m 36s
llama-run: add support for downloading models from ModelScope (#13370) CI #22328: Commit 0527771 pushed by ericcurtin
2h 58m 7s master
master
2h 58m 7s
server : PoC implementation of "interim" server CI #22327: Pull request #13400 opened by ngxson
1h 28m 34s ngxson:xsn/poc_interim_server
ngxson:xsn/poc_interim_server
1h 28m 34s
mtmd : fix batch_view for m-rope (#13397) CI #22326: Commit 2189fd3 pushed by ngxson
2h 19m 36s master
master
2h 19m 36s
llama : one-off chat template fix for Mistral-Small-2503 (#13398) CI #22325: Commit 3f96aef pushed by ngxson
1h 56m 52s master
master
1h 56m 52s
musa: restore MUSA graph settings in CMakeLists.txt CI #22324: Pull request #13382 synchronize by yeahdongcn
1h 19m 2s makllama:xd/graph
makllama:xd/graph
1h 19m 2s
llama : one-off chat template fix for Mistral-Small-2503 CI #22323: Pull request #13398 synchronize by ngxson
1h 43m 6s ngxson:xsn/oneoff_fix_mistral_tmpl
ngxson:xsn/oneoff_fix_mistral_tmpl
1h 43m 6s
llama : one-off chat template fix for Mistral-Small-2503 CI #22322: Pull request #13398 opened by ngxson
13m 35s ngxson:xsn/oneoff_fix_mistral_tmpl
ngxson:xsn/oneoff_fix_mistral_tmpl
13m 35s
mtmd : fix batch_view for m-rope CI #22321: Pull request #13397 synchronize by ngxson
1h 20m 37s ngxson:xsn/mtmd_fix_batch_view_mrope
ngxson:xsn/mtmd_fix_batch_view_mrope
1h 20m 37s
mtmd : fix batch_view for m-rope CI #22320: Pull request #13397 opened by ngxson
5m 51s ngxson:xsn/mtmd_fix_batch_view_mrope
ngxson:xsn/mtmd_fix_batch_view_mrope
5m 51s
rpc : add rpc_msg_set_tensor_hash_req (#13353) CI #22319: Commit b486ba0 pushed by rgerganov
1h 43m 45s master
master
1h 43m 45s
vulkan: Allow up to 4096 elements for mul_mat_id row_ids (#13326) CI #22318: Commit 02115dc pushed by 0cc4m
1h 4m 45s master
master
1h 4m 45s
vulkan: enable fp16 for gcn 3 and 4 chips CI #22317: Pull request #13396 opened by netrunnereve
47m 27s fp16
fp16
47m 27s
llama : do not crash if there is no CPU backend CI #22316: Pull request #13395 synchronize by slaren
44m 44s sl/fix-missing-cpu-backend-crash
sl/fix-missing-cpu-backend-crash
44m 44s
llama : do not crash if there is no CPU backend CI #22315: Pull request #13395 opened by slaren
14m 16s sl/fix-missing-cpu-backend-crash
sl/fix-missing-cpu-backend-crash
14m 16s