Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
37,856 workflow run results
37,856 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Tokenize logging Pull Request Labeler #11680: Pull request #13821 opened by koichog
15s
15s
gguf-py : add support for sub_type (in arrays) in GGUFWriter add_key_value method Pull Request Labeler #11679: Pull request #13561 synchronize by CISC
12s
12s
llama : validate seq id batch input (#13809) CI #23009: Commit 4f81b33 pushed by ggerganov
56m 4s master
master
56m 4s
llama : validate seq id batch input (#13809) Server #14405: Commit 4f81b33 pushed by ggerganov
11m 58s master
master
11m 58s
llama : validate seq id batch input (#13809) Release #155: Commit 4f81b33 pushed by ggerganov
20m 13s master
master
20m 13s
llama : validate seq id batch input (#13809) EditorConfig Checker #25854: Commit 4f81b33 pushed by ggerganov
20s master
master
20s
[WIP]backend: Integrating QNN (Qualcomm AI Engine Direct) as a dedicated backend for Qualcomm NPUs Pull Request Labeler #11678: Pull request #12063 synchronize by chraac
17s
17s
Update Winget Package Update Winget Package #6: Scheduled
19s master
master
19s
opencl: mark MUL_MAT supports non-contiguous tensors for f32 CI #23007: Pull request #13790 synchronize by lhez
57m 29s CodeLinaro:fix-supports-op-mul-mat-f32-f32
CodeLinaro:fix-supports-op-mul-mat-f32-f32
57m 29s
opencl: mark MUL_MAT supports non-contiguous tensors for f32 EditorConfig Checker #25852: Pull request #13790 synchronize by lhez
10m 57s CodeLinaro:fix-supports-op-mul-mat-f32-f32
CodeLinaro:fix-supports-op-mul-mat-f32-f32
10m 57s
opencl: mark MUL_MAT supports non-contiguous tensors for f32 Server #14403: Pull request #13790 synchronize by lhez
17m 47s CodeLinaro:fix-supports-op-mul-mat-f32-f32
CodeLinaro:fix-supports-op-mul-mat-f32-f32
17m 47s
opencl: mark MUL_MAT supports non-contiguous tensors for f32 Pull Request Labeler #11677: Pull request #13790 synchronize by lhez
10m 54s
10m 54s
Publish Docker image Publish Docker image #14962: Scheduled
1h 10m 59s master
master
1h 10m 59s
ggml: improve ggml_backend_cuda_cpy_tensor_async Pull Request Labeler #11676: Pull request #13818 synchronize by koush
26s
26s
ggml: improve ggml_backend_cuda_cpy_tensor_async Pull Request Labeler #11675: Pull request #13818 synchronize by koush
14s
14s
ggml: improve ggml_backend_cuda_cpy_tensor_async Pull Request Labeler #11674: Pull request #13818 opened by koush
1m 11s
1m 11s
[WIP]backend: Integrating QNN (Qualcomm AI Engine Direct) as a dedicated backend for Qualcomm NPUs Pull Request Labeler #11673: Pull request #12063 synchronize by chraac
14s
14s
vulkan: use timestamp queries for GGML_VULKAN_PERF CI #23003: Pull request #13817 opened by jeffbolznv
48m 37s jeffbolznv:query_pool
jeffbolznv:query_pool
48m 37s
vulkan: use timestamp queries for GGML_VULKAN_PERF EditorConfig Checker #25848: Pull request #13817 opened by jeffbolznv
20s jeffbolznv:query_pool
jeffbolznv:query_pool
20s
vulkan: use timestamp queries for GGML_VULKAN_PERF Pull Request Labeler #11672: Pull request #13817 opened by jeffbolznv
16s
16s
vulkan: use timestamp queries for GGML_VULKAN_PERF Server #14399: Pull request #13817 opened by jeffbolznv
10m 58s jeffbolznv:query_pool
jeffbolznv:query_pool
10m 58s
cuda: fix layer split mode preventing cuda graph compilation Pull Request Labeler #11671: Pull request #13815 opened by koush
13s
13s
Close inactive issues Close inactive issues #437: Scheduled
30s master
master
30s
ggml : allow CUDA graphs when using pipeline parallelism Server #14397: Pull request #13814 opened by slaren
10m 10s sl/fix-cuda-graphs-pp
sl/fix-cuda-graphs-pp
10m 10s
ggml : allow CUDA graphs when using pipeline parallelism CI #23001: Pull request #13814 opened by slaren
47m 17s sl/fix-cuda-graphs-pp
sl/fix-cuda-graphs-pp
47m 17s