Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
44,301 workflow run results
44,301 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ci : disable fast-math for Metal GHA CI Pull Request Labeler #12990: Pull request #14478 opened by ggerganov
1h 1m 13s
1h 1m 13s
test-backend-ops: add support for specifying output format Server #15735: Pull request #14368 synchronize by yeahdongcn
1h 17m 39s makllama:xd/test-backend-ops_sql
makllama:xd/test-backend-ops_sql
1h 17m 39s
test-backend-ops: add support for specifying output format EditorConfig Checker #27317: Pull request #14368 synchronize by yeahdongcn
1h 17m 39s makllama:xd/test-backend-ops_sql
makllama:xd/test-backend-ops_sql
1h 17m 39s
test-backend-ops: add support for specifying output format CI #24340: Pull request #14368 synchronize by yeahdongcn
1h 17m 52s makllama:xd/test-backend-ops_sql
makllama:xd/test-backend-ops_sql
1h 17m 52s
test-backend-ops: add support for specifying output format Pull Request Labeler #12989: Pull request #14368 synchronize by yeahdongcn
1h 47m 16s
1h 47m 16s
CUDA: add softmax broadcast Server #15734: Pull request #14475 synchronize by am17an
2h 18m 2s am17an:add_softmax_batch_and_broadcast
am17an:add_softmax_batch_and_broadcast
2h 18m 2s
CUDA: add softmax broadcast CI #24339: Pull request #14475 synchronize by am17an
2h 36m 38s am17an:add_softmax_batch_and_broadcast
am17an:add_softmax_batch_and_broadcast
2h 36m 38s
CUDA: add softmax broadcast Pull Request Labeler #12988: Pull request #14475 synchronize by am17an
1h 58m 24s
1h 58m 24s
CANN: update aclnnGroupedMatmulV2 to aclnnGroupedMatmulV3 (#14411) Release #380: Commit 343b6e9 pushed by hipudding
3h 27m 4s master
master
3h 27m 4s
CANN: update aclnnGroupedMatmulV2 to aclnnGroupedMatmulV3 (#14411) CI #24338: Commit 343b6e9 pushed by hipudding
4h 47m 17s master
master
4h 47m 17s
CANN: update aclnnGroupedMatmulV2 to aclnnGroupedMatmulV3 (#14411) EditorConfig Checker #27316: Commit 343b6e9 pushed by hipudding
1h 45m 20s master
master
1h 45m 20s
CANN: update aclnnGroupedMatmulV2 to aclnnGroupedMatmulV3 (#14411) Server #15733: Commit 343b6e9 pushed by hipudding
2h 31m 20s master
master
2h 31m 20s
vulkan: Split large mul_mat_id to fit in shared memory (#14451) CI #24337: Commit 6a746cf pushed by 0cc4m
4h 13m 29s master
master
4h 13m 29s
vulkan: Split large mul_mat_id to fit in shared memory (#14451) EditorConfig Checker #27315: Commit 6a746cf pushed by 0cc4m
1h 26m 56s master
master
1h 26m 56s
vulkan: Split large mul_mat_id to fit in shared memory (#14451) Server #15732: Commit 6a746cf pushed by 0cc4m
2h 20m 0s master
master
2h 20m 0s
vulkan: Split large mul_mat_id to fit in shared memory (#14451) Release #379: Commit 6a746cf pushed by 0cc4m
3h 0m 25s master
master
3h 0m 25s
opencl : add GELU_ERF CI #24336: Pull request #14476 opened by CISC
3h 1m 15s cisc/opencl-gelu-erf
cisc/opencl-gelu-erf
3h 1m 15s
opencl : add GELU_ERF EditorConfig Checker #27314: Pull request #14476 opened by CISC
1h 7m 13s cisc/opencl-gelu-erf
cisc/opencl-gelu-erf
1h 7m 13s
opencl : add GELU_ERF Server #15731: Pull request #14476 opened by CISC
1h 58m 41s cisc/opencl-gelu-erf
cisc/opencl-gelu-erf
1h 58m 41s
opencl : add GELU_ERF Pull Request Labeler #12987: Pull request #14476 opened by CISC
1h 13m 1s
1h 13m 1s
CUDA: add softmax broadcast Server #15730: Pull request #14475 opened by am17an
25m 12s am17an:add_softmax_batch_and_broadcast
am17an:add_softmax_batch_and_broadcast
25m 12s
CUDA: add softmax broadcast CI #24335: Pull request #14475 opened by am17an
25m 16s am17an:add_softmax_batch_and_broadcast
am17an:add_softmax_batch_and_broadcast
25m 16s
CUDA: add softmax broadcast Pull Request Labeler #12986: Pull request #14475 opened by am17an
53m 16s
53m 16s
ggml : support broadcast for ggml_soft_max_ext and ggml_flash_attn_ext Server #15729: Pull request #14435 synchronize by 0cc4m
1h 10m 51s gg/ggml-batch-soft-max-ops
gg/ggml-batch-soft-max-ops
1h 10m 51s
ggml : support broadcast for ggml_soft_max_ext and ggml_flash_attn_ext CI #24334: Pull request #14435 synchronize by 0cc4m
2h 13m 27s gg/ggml-batch-soft-max-ops
gg/ggml-batch-soft-max-ops
2h 13m 27s