Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
7,070 workflow run results
7,070 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

opencl: add backend_synchronize (#13939) CI #23336: Commit 71e74a3 pushed by max-krasnyansky
1h 11m 38s master
master
1h 11m 38s
OpenCL: Add concat, tsembd, upscale, tanh, pad and repeat (#13840) CI #23335: Commit bfb1e01 pushed by max-krasnyansky
50m 18s master
master
50m 18s
llama : support multiple classifier outputs and labels CI #23334: Pull request #13940 synchronize by CISC
1m 50s cisc/multiple-classifier-outputs
cisc/multiple-classifier-outputs
1m 50s
llama : support multiple classifier outputs and labels CI #23333: Pull request #13940 synchronize by CISC
22m 59s cisc/multiple-classifier-outputs
cisc/multiple-classifier-outputs
22m 59s
llama : allow building all tests on windows when not using shared libs CI #23332: Pull request #13980 opened by slaren
1h 1m 39s sl/tests-windows-shared-libs
sl/tests-windows-shared-libs
1h 1m 39s
Hybrid recurrent cache CI #23330: Pull request #13979 opened by gabe-l-hart
50m 7s gabe-l-hart:HybridRecurrentCache
gabe-l-hart:HybridRecurrentCache
50m 7s
server : disable speculative decoding for SWA models (#13970) CI #23329: Commit 3637576 pushed by ggerganov
1h 35m 9s master
master
1h 35m 9s
metal : use F32 accumulators in FA kernels (#13975) CI #23328: Commit ea394d7 pushed by ggerganov
1h 6m 3s master
master
1h 6m 3s
server : disable speculative decoding for SWA models CI #23327: Pull request #13970 synchronize by ggerganov
56m 57s gg/server-spec-swa-clear
gg/server-spec-swa-clear
56m 57s
gemma : more consistent attention scaling for v2 and v3 (#13951) CI #23326: Commit 5582c49 pushed by ggerganov
1h 0m 11s master
master
1h 0m 11s
server: update deepseek reasoning format (pass reasoning_content as… CI #23325: Commit c9bbc77 pushed by ochafik
1h 0m 15s master
master
1h 0m 15s
metal : use F32 attention accumulators in FA kernels CI #23324: Pull request #13975 opened by ggerganov
58m 49s gg/metal-fa-acc-f32
gg/metal-fa-acc-f32
58m 49s
gemma : more consistent attention scaling for v2 and v3 CI #23323: Pull request #13951 synchronize by ggerganov
56m 38s gg/gemma-fix-attn-scale
gg/gemma-fix-attn-scale
56m 38s
mtmd : fix memory leak in mtmd_helper_eval_chunk_single (#13961) CI #23322: Commit bfd3227 pushed by ngxson
1h 7m 19s master
master
1h 7m 19s
sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel Devices CI #23321: Pull request #13973 opened by ShanoToni
1h 11m 15s ShanoToni:reorder_intel_on_by_default
ShanoToni:reorder_intel_on_by_default
1h 11m 15s
server : disable speculative decoding for SWA models CI #23320: Pull request #13970 opened by ggerganov
1h 2m 37s gg/server-spec-swa-clear
gg/server-spec-swa-clear
1h 2m 37s
mtmd : fix memory leak in mtmd_helper_eval_chunk_single CI #23319: Pull request #13961 synchronize by ngxson
51m 13s ngxson:xsn/memleak_mtmd_helper
ngxson:xsn/memleak_mtmd_helper
51m 13s
cmake : Handle mixed-case 'Power' strings in POWER CPU detection (#13… CI #23318: Commit 093e3f1 pushed by ggerganov
56m 33s master
master
56m 33s
llama : support multiple classifier outputs and labels CI #23317: Pull request #13940 synchronize by CISC
1h 27m 26s cisc/multiple-classifier-outputs
cisc/multiple-classifier-outputs
1h 27m 26s
"Fix: Handle mixed-case 'Power' strings in POWER CPU detection" CI #23316: Pull request #13966 synchronize by shalinib-ibm
1h 1m 17s shalinib-ibm:p11_bug_fix
shalinib-ibm:p11_bug_fix
1h 1m 17s
"Fix: Handle mixed-case 'Power' strings in POWER CPU detection" CI #23315: Pull request #13966 opened by shalinib-ibm
3m 48s shalinib-ibm:p11_bug_fix
shalinib-ibm:p11_bug_fix
3m 48s
sycl: quantize and reorder the input to q8_1 when reorder is enabled … CI #23314: Commit 663445b pushed by Alcpz
1h 0m 26s master
master
1h 0m 26s
mtmd : fix memory leak in mtmd_helper_eval_chunk_single CI #23313: Pull request #13961 synchronize by ngxson
52m 40s ngxson:xsn/memleak_mtmd_helper
ngxson:xsn/memleak_mtmd_helper
52m 40s
llama : support multiple classifier outputs and labels CI #23312: Pull request #13940 synchronize by CISC
49m 2s cisc/multiple-classifier-outputs
cisc/multiple-classifier-outputs
49m 2s
mtmd : fix memory leak in mtmd_helper_eval_chunk_single CI #23311: Pull request #13961 opened by ngxson
50m 26s ngxson:xsn/memleak_mtmd_helper
ngxson:xsn/memleak_mtmd_helper
50m 26s