Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
4,781 workflow run results
4,781 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

change cpu_buft_list order: ACCEL -> GPU host -> CPU extra -> CPU CI #20750: Pull request #12632 opened by Djip007
49m 32s Djip007:patch/cpu_buffer_reorder
Djip007:patch/cpu_buffer_reorder
49m 32s
llama : fix incorrect Qwen2Moe ffn_moe_out graph callback CI #20749: Pull request #12631 opened by CISC
1h 6m 29s CISC:qwen2moe-cb-fix
CISC:qwen2moe-cb-fix
1h 6m 29s
ci: add Linux cross-compile build CI #20748: Pull request #12428 synchronize by bandoti
29m 37s bandoti:ci-build-cross
bandoti:ci-build-cross
29m 37s
vulkan: Hybrid waitForFences/getFenceStatus to reduce fence latency CI #20747: Pull request #12630 synchronize by jeffbolznv
54m 28s jeffbolznv:spin_fence
jeffbolznv:spin_fence
54m 28s
metal : improve FA + improve MoE (#12612) CI #20746: Commit b4ae508 pushed by ggerganov
45m 59s master
master
45m 59s
vulkan: fix coopmat shader generation when cross-compiling (#12272) CI #20745: Commit b86f600 pushed by bandoti
1h 5m 51s master
master
1h 5m 51s
llama: fix error on bad grammar (#12628) CI #20744: Commit dd373dd pushed by JohannesGaessler
1h 5m 52s master
master
1h 5m 52s
vulkan: fix coopmat shader generation when cross-compiling CI #20743: Pull request #12272 synchronize by bandoti
1h 25m 54s Icenowy:vk-coopmat-cross
Icenowy:vk-coopmat-cross
1h 25m 54s
SYCL: Rename oneMKL to oneMath CI #20742: Pull request #12192 synchronize by Rbiessy
1h 25m 52s Rbiessy:romain/rename_onemath
Rbiessy:romain/rename_onemath
1h 25m 52s
vulkan: fix coopmat shader generation when cross-compiling CI #20741: Pull request #12272 synchronize by bandoti
4m 17s Icenowy:vk-coopmat-cross
Icenowy:vk-coopmat-cross
4m 17s
vulkan: Hybrid waitForFences/getFenceStatus to reduce fence latency CI #20740: Pull request #12630 opened by jeffbolznv
1h 3m 36s jeffbolznv:spin_fence
jeffbolznv:spin_fence
1h 3m 36s
metal : improve FA + improve MoE CI #20739: Pull request #12612 synchronize by ggerganov
1h 13m 39s gg/metal-fa-diff-heads
gg/metal-fa-diff-heads
1h 13m 39s
llama: fix error on bad grammar CI #20738: Pull request #12628 opened by JohannesGaessler
1h 6m 43s JohannesGaessler:server-grammar-fix
JohannesGaessler:server-grammar-fix
1h 6m 43s
Add Yandex instruct model template support CI #20736: Pull request #12621 synchronize by vorobyov01
4m 18s vorobyov01:master
vorobyov01:master
4m 18s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp CI #20735: Pull request #12326 synchronize by jeffzhou2000
1h 12m 27s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
1h 12m 27s
metal : improve FA + improve MoE CI #20734: Pull request #12612 synchronize by ggerganov
59m 33s gg/metal-fa-diff-heads
gg/metal-fa-diff-heads
59m 33s
vulkan: Implement split_k for coopmat2 flash attention. CI #20733: Pull request #12627 opened by jeffbolznv
47m 57s jeffbolznv:flash_split_k
jeffbolznv:flash_split_k
47m 57s
metal : improve FA + improve MoE CI #20732: Pull request #12612 synchronize by ggerganov
29m 28s gg/metal-fa-diff-heads
gg/metal-fa-diff-heads
29m 28s
musa: fix all warnings, re-enable -DLLAMA_FATAL_WARNINGS=ON in ci and update doc CI #20731: Pull request #12611 synchronize by yeahdongcn
41m 14s makllama:xd/warnings_musa
makllama:xd/warnings_musa
41m 14s
metal : improve FA + improve MoE CI #20730: Pull request #12612 synchronize by ggerganov
47m 53s gg/metal-fa-diff-heads
gg/metal-fa-diff-heads
47m 53s
sycl: allow ggml-sycl configuration and compilation using Visual Studio project/solution CI #20729: Pull request #12625 opened by s-Nick
45m 0s s-Nick:windows_vs_proj
s-Nick:windows_vs_proj
45m 0s
opencl: Add support for multiple devices CI #20728: Pull request #12622 opened by linehill
44m 15s linehill:ocl-mdev
linehill:ocl-mdev
44m 15s
server : include speculative decoding stats when timings_per_token is… CI #20727: Commit 5d01670 pushed by ggerganov
54m 47s master
master
54m 47s
llamafile : ppc64le GEMV forwarding for FP32. (#12594) CI #20725: Commit 1373176 pushed by ggerganov
50m 11s master
master
50m 11s
rpc : send hash when tensor data is above some fixed threshold (#12496) CI #20724: Commit ab6ab8f pushed by rgerganov
47m 16s master
master
47m 16s