Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
44,144 workflow run results
44,144 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml: fix typo in ggml.c EditorConfig Checker #27464: Pull request #14531 opened by jeffzhou2000
17s jeffzhou2000:fix_typo
jeffzhou2000:fix_typo
17s
ggml: fix typo in ggml.c CI #24480: Pull request #14531 opened by jeffzhou2000
1h 2m 37s jeffzhou2000:fix_typo
jeffzhou2000:fix_typo
1h 2m 37s
ggml: fix typo in ggml.c Server #15875: Pull request #14531 opened by jeffzhou2000
12m 36s jeffzhou2000:fix_typo
jeffzhou2000:fix_typo
12m 36s
ggml: fix typo in ggml.c Pull Request Labeler #13117: Pull request #14531 opened by jeffzhou2000
13s
13s
llama : add high-throughput mode EditorConfig Checker #27463: Pull request #14363 synchronize by ggerganov
17s gg/llama-high-throughput
gg/llama-high-throughput
17s
llama : add high-throughput mode CI #24479: Pull request #14363 synchronize by ggerganov
1h 3m 1s gg/llama-high-throughput
gg/llama-high-throughput
1h 3m 1s
llama : add high-throughput mode Server #15874: Pull request #14363 synchronize by ggerganov
12m 22s gg/llama-high-throughput
gg/llama-high-throughput
12m 22s
llama : add high-throughput mode Pull Request Labeler #13116: Pull request #14363 synchronize by ggerganov
10s
10s
CUDA: add bf16 and i32 to getrows Server #15873: Pull request #14529 opened by am17an
11m 10s am17an:cuda_bf16_i32_get_rows
am17an:cuda_bf16_i32_get_rows
11m 10s
CUDA: add bf16 and i32 to getrows EditorConfig Checker #27462: Pull request #14529 opened by am17an
2m 1s am17an:cuda_bf16_i32_get_rows
am17an:cuda_bf16_i32_get_rows
2m 1s
CUDA: add bf16 and i32 to getrows CI #24478: Pull request #14529 opened by am17an
1h 4m 27s am17an:cuda_bf16_i32_get_rows
am17an:cuda_bf16_i32_get_rows
1h 4m 27s
CUDA: add bf16 and i32 to getrows Pull Request Labeler #13115: Pull request #14529 opened by am17an
13s
13s
metal : disable fast math in all quantize kernels EditorConfig Checker #27461: Pull request #14528 opened by ggerganov
17s gg/metal-fast-math-spec-cont
gg/metal-fast-math-spec-cont
17s
metal : disable fast math in all quantize kernels CI #24477: Pull request #14528 opened by ggerganov
1h 2m 30s gg/metal-fast-math-spec-cont
gg/metal-fast-math-spec-cont
1h 2m 30s
metal : disable fast math in all quantize kernels Pull Request Labeler #13114: Pull request #14528 opened by ggerganov
12s
12s
llama : add high-throughput mode Server #15872: Pull request #14363 synchronize by ggerganov
30m 16s gg/llama-high-throughput
gg/llama-high-throughput
30m 16s
llama : add high-throughput mode EditorConfig Checker #27460: Pull request #14363 synchronize by ggerganov
20m 15s gg/llama-high-throughput
gg/llama-high-throughput
20m 15s
llama : add high-throughput mode CI #24476: Pull request #14363 synchronize by ggerganov
1h 11m 48s gg/llama-high-throughput
gg/llama-high-throughput
1h 11m 48s
llama : add high-throughput mode Pull Request Labeler #13113: Pull request #14363 synchronize by ggerganov
2m 40s
2m 40s
kv-cache : prepare K/V buffers for separation EditorConfig Checker #27459: Pull request #14517 synchronize by ggerganov
15m 55s gg/kv-cache-prepare-separation
gg/kv-cache-prepare-separation
15m 55s
kv-cache : prepare K/V buffers for separation CI #24475: Pull request #14517 synchronize by ggerganov
1h 19m 56s gg/kv-cache-prepare-separation
gg/kv-cache-prepare-separation
1h 19m 56s
kv-cache : prepare K/V buffers for separation Server #15871: Pull request #14517 synchronize by ggerganov
1h 5m 30s gg/kv-cache-prepare-separation
gg/kv-cache-prepare-separation
1h 5m 30s
kv-cache : prepare K/V buffers for separation Pull Request Labeler #13112: Pull request #14517 synchronize by ggerganov
16m 50s
16m 50s
llama : add high-throughput mode CI #24474: Pull request #14363 synchronize by ggerganov
50m 57s gg/llama-high-throughput
gg/llama-high-throughput
50m 57s
llama : add high-throughput mode EditorConfig Checker #27458: Pull request #14363 synchronize by ggerganov
20s gg/llama-high-throughput
gg/llama-high-throughput
20s