Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
43,111 workflow run results
43,111 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

batch : fix check for empty sequences in memory EditorConfig Checker #27060: Pull request #14364 opened by ggerganov
18s gg/batch-fix-empty-check
gg/batch-fix-empty-check
18s
batch : fix check for empty sequences in memory Server #15494: Pull request #14364 opened by ggerganov
7m 3s gg/batch-fix-empty-check
gg/batch-fix-empty-check
7m 3s
batch : fix check for empty sequences in memory CI #24098: Pull request #14364 opened by ggerganov
7m 14s gg/batch-fix-empty-check
gg/batch-fix-empty-check
7m 14s
ggml-cpu: enable IBM NNPA Vector Intrinsics Server #15493: Pull request #14317 synchronize by taronaeo
35m 41s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
35m 41s
ggml-cpu: enable IBM NNPA Vector Intrinsics Pull Request Labeler #12748: Pull request #14317 synchronize by taronaeo
18m 35s
18m 35s
ggml-cpu: enable IBM NNPA Vector Intrinsics EditorConfig Checker #27059: Pull request #14317 synchronize by taronaeo
5m 32s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
5m 32s
ggml-cpu: enable IBM NNPA Vector Intrinsics CI #24097: Pull request #14317 synchronize by taronaeo
1h 24m 0s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
1h 24m 0s
ggml-cpu: enable IBM NNPA Vector Intrinsics EditorConfig Checker #27058: Pull request #14317 synchronize by taronaeo
19m 26s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
19m 26s
ggml-cpu: enable IBM NNPA Vector Intrinsics Server #15492: Pull request #14317 synchronize by taronaeo
19m 28s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
19m 28s
ggml-cpu: enable IBM NNPA Vector Intrinsics CI #24096: Pull request #14317 synchronize by taronaeo
19m 45s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
19m 45s
ggml-cpu: enable IBM NNPA Vector Intrinsics Pull Request Labeler #12747: Pull request #14317 synchronize by taronaeo
19m 45s
19m 45s
cmake : use LLAMA_BUILD_NUMBER when defining LLAMA_INSTALL_VERSION (#… Release #344: Commit c148cf1 pushed by ckastner
1h 16m 17s master
master
1h 16m 17s
cmake : use LLAMA_BUILD_NUMBER when defining LLAMA_INSTALL_VERSION (#… EditorConfig Checker #27057: Commit c148cf1 pushed by ckastner
3m 55s master
master
3m 55s
cmake : use LLAMA_BUILD_NUMBER when defining LLAMA_INSTALL_VERSION (#… Server #15491: Commit c148cf1 pushed by ckastner
1h 2m 49s master
master
1h 2m 49s
cmake : use LLAMA_BUILD_NUMBER when defining LLAMA_INSTALL_VERSION (#… CI #24095: Commit c148cf1 pushed by ckastner
1h 35m 28s master
master
1h 35m 28s
llama : add high-throughput mode Server #15490: Pull request #14363 synchronize by ggerganov
1h 4m 32s gg/llama-high-throughput
gg/llama-high-throughput
1h 4m 32s
llama : add high-throughput mode CI #24094: Pull request #14363 synchronize by ggerganov
1h 38m 57s gg/llama-high-throughput
gg/llama-high-throughput
1h 38m 57s
llama : add high-throughput mode Pull Request Labeler #12746: Pull request #14363 synchronize by ggerganov
28m 38s
28m 38s
ggml-cpu: enable IBM NNPA Vector Intrinsics Server #15489: Pull request #14317 synchronize by taronaeo
27m 29s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
27m 29s
ggml-cpu: enable IBM NNPA Vector Intrinsics CI #24093: Pull request #14317 synchronize by taronaeo
27m 49s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
27m 49s
ggml-cpu: enable IBM NNPA Vector Intrinsics EditorConfig Checker #27056: Pull request #14317 synchronize by taronaeo
11m 19s taronaeo:feat/nnpa-fp16-rework
taronaeo:feat/nnpa-fp16-rework
11m 19s
ggml-cpu: enable IBM NNPA Vector Intrinsics Pull Request Labeler #12745: Pull request #14317 synchronize by taronaeo
21m 36s
21m 36s
CUDA: add bf16 and f32 support to cublas_mul_mat_batched Server #15488: Pull request #14361 synchronize by am17an
19m 51s am17an:add_bp16_fp32_to_cublas_batched
am17an:add_bp16_fp32_to_cublas_batched
19m 51s
CUDA: add bf16 and f32 support to cublas_mul_mat_batched EditorConfig Checker #27055: Pull request #14361 synchronize by am17an
54s am17an:add_bp16_fp32_to_cublas_batched
am17an:add_bp16_fp32_to_cublas_batched
54s
CUDA: add bf16 and f32 support to cublas_mul_mat_batched CI #24092: Pull request #14361 synchronize by am17an
1h 26m 50s am17an:add_bp16_fp32_to_cublas_batched
am17an:add_bp16_fp32_to_cublas_batched
1h 26m 50s