Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
10,695 workflow run results
10,695 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Deepseek V3.1 native tool calling support (OpenAI Style) CI #27247: Pull request #15533 synchronize by createthis
3h 45m 21s createthis:deepseek_3_1_thinking_mode
createthis:deepseek_3_1_thinking_mode
3h 45m 21s
Deepseek V3.1 native tool calling support (OpenAI Style) CI #27246: Pull request #15533 synchronize by createthis
5m 43s createthis:deepseek_3_1_thinking_mode
createthis:deepseek_3_1_thinking_mode
5m 43s
Feat: Apertus model implementation CI #27243: Pull request #15852 synchronize by pwilkin
3h 14m 36s pwilkin:apertus-implementation
pwilkin:apertus-implementation
3h 14m 36s
metal : make the backend async CI #27242: Pull request #15832 synchronize by ggerganov
3h 11m 30s gg/metal-async
gg/metal-async
3h 11m 30s
Feat: Apertus model implementation CI #27241: Pull request #15852 synchronize by pwilkin
5m 23s pwilkin:apertus-implementation
pwilkin:apertus-implementation
5m 23s
Feat: Apertus model implementation CI #27240: Pull request #15852 synchronize by pwilkin
7m 12s pwilkin:apertus-implementation
pwilkin:apertus-implementation
7m 12s
metal : refactor + optimize (#15857) CI #27239: Commit f28d4f4 pushed by ggerganov
5h 44m 37s master
master
5h 44m 37s
ggml: allow casting between f32 and i32 (#15783) CI #27238: Commit 9fcb29f pushed by ngxson
3h 41m 25s master
master
3h 41m 25s
webgpu : fix build on emscripten CI #27237: Pull request #15826 synchronize by ngxson
3h 47m 12s ngxson:xsn/emscripten_webgpu
ngxson:xsn/emscripten_webgpu
3h 47m 12s
metal : refactor + optimize CI #27236: Pull request #15857 synchronize by ggerganov
3h 12m 31s gg/metal-refactor
gg/metal-refactor
3h 12m 31s
CUDA: non-contiguous src0 not supported for PAD (#15869) CI #27235: Commit 5ef22d2 pushed by ggerganov
2h 14m 46s master
master
2h 14m 46s
metal : refactor + optimize CI #27234: Pull request #15857 synchronize by ggerganov
39m 28s gg/metal-refactor
gg/metal-refactor
39m 28s
cuda : fix supports_op condition for get_rows when number of blocks is too large CI #27233: Pull request #15868 synchronize by ggerganov
1h 38m 16s gg/cuda-fix-supports-get-rows
gg/cuda-fix-supports-get-rows
1h 38m 16s
CUDA: Add fastdiv to k_bin_bcast*, giving 1-3% E2E performance CI #27232: Pull request #15872 opened by ORippler
1h 46m 49s ORippler:osimons/add_fastdiv_to_k_bin_bcast
ORippler:osimons/add_fastdiv_to_k_bin_bcast
1h 46m 49s
cuda : fix supports_op condition for get_rows when number of blocks is too large CI #27231: Pull request #15868 synchronize by ggerganov
30m 51s gg/cuda-fix-supports-get-rows
gg/cuda-fix-supports-get-rows
30m 51s
model-conversion : add embedding prompt file support CI #27230: Pull request #15871 opened by danbev
4h 9m 59s danbev:model-conversion-prompt-file-support
danbev:model-conversion-prompt-file-support
4h 9m 59s
cuda : non-contiguous src0 not supported for PAD CI #27229: Pull request #15869 opened by CISC
2h 17m 49s cisc/cuda-pad-contiguous-src0-check
cisc/cuda-pad-contiguous-src0-check
2h 17m 49s
batched-bench : fix llama_synchronize usage during prompt processing … CI #27228: Commit a885dcf pushed by ggerganov
3h 54m 50s master
master
3h 54m 50s
context : fix n_outputs during reserve (#15858) CI #27227: Commit 663027f pushed by ggerganov
1h 32m 39s master
master
1h 32m 39s
cuda : fix supports_op condition for get_rows when number of blocks is too large CI #27226: Pull request #15868 opened by ggerganov
1h 3m 24s gg/cuda-fix-supports-get-rows
gg/cuda-fix-supports-get-rows
1h 3m 24s
model : avoid ggml_cont_3d for fused QKV weights CI #27225: Pull request #15662 synchronize by ggerganov
1h 9m 17s gg/model-avoid-cont3d
gg/model-avoid-cont3d
1h 9m 17s
model : avoid ggml_cont_3d for fused QKV weights CI #27224: Pull request #15662 synchronize by ggerganov
3m 59s gg/model-avoid-cont3d
gg/model-avoid-cont3d
3m 59s
model : avoid ggml_cont_3d for fused QKV weights CI #27223: Pull request #15662 synchronize by ggerganov
3m 56s gg/model-avoid-cont3d
gg/model-avoid-cont3d
3m 56s
model : avoid ggml_cont_3d for fused QKV weights CI #27222: Pull request #15662 synchronize by ggerganov
3m 14s gg/model-avoid-cont3d
gg/model-avoid-cont3d
3m 14s
nix: Added missing packages and options for ROCm build CI #27221: Pull request #15747 synchronize by SteelPh0enix
1h 4m 15s SteelPh0enix:nix-rocm-tweaks
SteelPh0enix:nix-rocm-tweaks
1h 4m 15s